# Humanoid Robots

Humanoid robots are robotic systems designed with a human-like body structure, drawing on mechanical engineering, control theory, computer vision, and machine learning for movement, perception, and interaction.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Decapitation Seems Like a Great Way to Start X-Mas Decorating

DevFeed: [Decapitation Seems Like a Great Way to Start X-Mas Decorating](<https://devfeed.tech/articles/decapitation-seems-like-a-great-way-to-start-x-mas-decorating-146820.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/11/20/decapitation-seems-like-a-great-way-to-start-x-mas-decorating/>)

Author: Tyler August

Published: 2026-11-21T00:00:51Z

Content type: news

Language: en

Sources: [Hackaday](<https://devfeed.tech/sources/hackaday.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [D](<https://devfeed.tech/topics/d.md>)

Tags: [3d-printed](<https://devfeed.tech/tags/3d-printed.md>), [animatronic](<https://devfeed.tech/tags/animatronic.md>), [animatronics](<https://devfeed.tech/tags/animatronics.md>), [c](<https://devfeed.tech/tags/c.md>), [easing](<https://devfeed.tech/tags/easing.md>), [github](<https://devfeed.tech/tags/github.md>), [hobby-servo](<https://devfeed.tech/tags/hobby-servo.md>), [holiday-hack](<https://devfeed.tech/tags/holiday-hack.md>), [holiday-hacks](<https://devfeed.tech/tags/holiday-hacks.md>), [library](<https://devfeed.tech/tags/library.md>), [pan-tilt](<https://devfeed.tech/tags/pan-tilt.md>), [pi-pico-2w](<https://devfeed.tech/tags/pi-pico-2w.md>), [pico](<https://devfeed.tech/tags/pico.md>), [puppet](<https://devfeed.tech/tags/puppet.md>), [radar](<https://devfeed.tech/tags/radar.md>), [servo](<https://devfeed.tech/tags/servo.md>), [snowman](<https://devfeed.tech/tags/snowman.md>), [state-machine](<https://devfeed.tech/tags/state-machine.md>)

### AI overview

A felt snowman puppet becomes an interactive animatronic using four servos controlled by a Pico 2W, which receives input from a 24 GHz radar module. It waves, tracks nearby people, and nods and gestures when someone stands in front of it. Its roughly 300 lines of C implement a state machine, with servo easing to make movements look more lifelike. The builder also released the servo library separately. Fitting the 3D-printed frame required removing the puppet's head. These details come from the supplied excerpt.

### Source excerpt

American cultural osmosis being what it is, it's likely more people know the story of Frosty the Snowman than have ever actually had the chance to build a snowman. What ...read more

## Reference-Free Humanoid Skateboarding via Termination-Shaped Reinforcement Learning

DevFeed: [Reference-Free Humanoid Skateboarding via Termination-Shaped Reinforcement Learning](<https://devfeed.tech/articles/reference-free-humanoid-skateboarding-via-termination-shaped-reinforcement-learning-145131.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26054>)

Author: Ganeshvar Soenessardien, Michael Przystupa, Kevin Sebastian Luck

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>)

Tags: [board](<https://devfeed.tech/tags/board.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [deep-reinforcement-learning](<https://devfeed.tech/tags/deep-reinforcement-learning.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [model](<https://devfeed.tech/tags/model.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

The paper presents model-free deep reinforcement learning for teaching the K1 humanoid to skateboard without demonstrations or analytic steering models requiring system identification. It combines task rewards with termination constraints that block behaviors including losing the planted board foot, putting both feet on the board, excessive twisting, separating from the board, and unstable board motion. As these behaviors become less prevalent during training, the constraints produce an implicit progression from stance control toward sustained robot-board locomotion.

### Source excerpt

arXiv:2611.26054v1 Announce Type: cross Abstract: Humanoid locomotion research has advanced rapidly on walking and running, but \emph {object-mediated} locomotion, in which a robot must coordinate its body with a passive external object, remains difficult. One challenging task is skateboarding, which requires simultaneous interaction with the ground and a passive but movable platform to achieve forward motion. Current methods for tackling skateboarding with humanoid robots either require human demonstrations or utilise analytic steering models that require system identification. In this paper, we introduce a deep reinforcement learning framework that does not rely on prior data such as demonstrations and enables robots such as the K1 humanoid to learn to skateboard using model-free learning. The method combines task rewards with exploit-blocking terminations. We introduce a number of constraints restricting behaviours such as losing the planted board foot, standing with both feet on the board, excessive twisting, separation from the board, and unstable board motion. Their changing prevalence during training produces an implicit progression from stance control towards sustained robot--board locomotion.

## PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation

DevFeed: [PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation](<https://devfeed.tech/articles/pgx-physically-grounded-execution-for-long-horizon-humanoid-loco-manipulation-145692.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26596>)

Author: Kai Lu, Chenyang Ma, Ioannis Havoutis

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [Robot Navigation](<https://devfeed.tech/topics/robot-navigation.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [base](<https://devfeed.tech/tags/base.md>), [based](<https://devfeed.tech/tags/based.md>), [components](<https://devfeed.tech/tags/components.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [flat](<https://devfeed.tech/tags/flat.md>), [focus](<https://devfeed.tech/tags/focus.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gate](<https://devfeed.tech/tags/gate.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoid-robot](<https://devfeed.tech/tags/humanoid-robot.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [language](<https://devfeed.tech/tags/language.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>)

### AI overview

PGX addresses long-horizon humanoid loco-manipulation by separating task progression and spatial precision from VLA skill execution. A predicate-based state machine gates phase changes, triggers recovery, and coordinates navigation and waiting; shared predicate semantics also link demonstration segmentation, execution, and stage-wise evaluation. Within each active manipulation phase, flat or stage-trained VLA models focus on relevant actions. Training-free world-coordinate locking maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. Experiments on three simulated tasks and one real-world task with a Unitree G1 report improved stage progression and task success rates; the excerpt provides no quantitative results.

### Source excerpt

arXiv:2611.26596v1 Announce Type: cross Abstract: Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (PGX), a framework that offloads temporal and precision control to two classical training-free components, allowing the VLA to focus on stage-specific skill dynamics. PGX decomposes long-horizon loco-manipulation into three layers: (i) a predicate-based state machine governs task progression, using physical predicates to gate phase transitions, trigger recovery, and coordinate navigation and waiting. Shared predicate semantics connect offline demonstration segmentation, online execution, and stage-wise evaluation; (ii) VLA skills operate within active manipulation phases, with flat or stage-trained models concentrating on task-relevant actions; and (iii) world-coordinate locking (WCL) maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. We demonstrate the effectiveness of PGX with extensive experiments conducted on three simulated tasks and one real-world task using a Unitree G1 humanoid robot for long-horizon loco-manipulation, showing improvements in stage progression and task success rates. Project page is available at: https://kl-research.github.io/pgx

## Controlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible Network

DevFeed: [Controlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible Network](<https://devfeed.tech/articles/controlling-the-humanoid-robot-h1-2-with-a-simulated-biologically-plausible-network-145630.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26074>)

Author: Fatima Atwi (LAAS-GEPETTO, Nantes Univ - ECN), Constant Roux (LAAS-GEPETTO), Christian Bergaud (LAAS-MEMS), Olivier Stasse (LAAS-GEPETTO)

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [backpropagation](<https://devfeed.tech/tags/backpropagation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [culture](<https://devfeed.tech/tags/culture.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [e-prop](<https://devfeed.tech/tags/e-prop.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoid-robot](<https://devfeed.tech/tags/humanoid-robot.md>), [learning](<https://devfeed.tech/tags/learning.md>), [matching](<https://devfeed.tech/tags/matching.md>), [network](<https://devfeed.tech/tags/network.md>), [performance](<https://devfeed.tech/tags/performance.md>), [plasticity](<https://devfeed.tech/tags/plasticity.md>), [recurrent](<https://devfeed.tech/tags/recurrent.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [robust](<https://devfeed.tech/tags/robust.md>), [spiking-neural-networks](<https://devfeed.tech/tags/spiking-neural-networks.md>), [stdp](<https://devfeed.tech/tags/stdp.md>), [survival](<https://devfeed.tech/tags/survival.md>), [trends](<https://devfeed.tech/tags/trends.md>), [unitree](<https://devfeed.tech/tags/unitree.md>)

### AI overview

The study compares three learning schemes for a biologically inspired spiking network controlling the Unitree H1-2 humanoid. All use distillation of a reinforcement-learning expert policy with dataset aggregation. The fixed-reservoir approach freezes recurrent weights and trains only a linear readout; reward-modulated STDP with eligibility propagation trains synapses; backpropagation through time serves as a non-biological baseline. E-prop achieved a 100% survival rate, matching backpropagation through time, while the fixed reservoir and reward-modulated STDP reached about 43.7% and 11%, respectively. The authors also report brief bipedal stepping on the full-size robot. These findings, as presented in the abstract, show a performance gap between e-prop and the two approaches described as closest to biological cultures.

### Source excerpt

arXiv:2611.26074v1 Announce Type: new Abstract: Artificial Spiking Neural Networks have gained remarkable attention in the last few years due to their proven ability in simulating biological neural cultures and producing similar activity and trends. Nevertheless, whether they can be trained for humanoid locomotion while retaining biological plausibility and robust performance at once remains an open question. We study this problem by proposing a biologically inspired spiking network, trained by different learning schemes and tested on the H1-2 Unitree Humanoid. These schemes differ in how recurrent weights are trained. Ordered from most to least biologically faithful, they are: a fixed reservoir mimicking an in-vitro neural culture, where recurrent weights are kept frozen and only a linear readout is trained, the same network but with its synapses trained by reward-modulated spike timing dependent plasticity and eligibility propagation, and finally backpropagation through time as a non biological baseline for comparison. All schemes relied on distillation of a reinforcement learning expert policy with dataset aggregation. We show that e-prop reached 100% survival rate matching backpropagation through time, whereas both the fixed reservoir and the reward-modulated STDP, though the closest to biological cultures, plateaued at a much lower performance (~43.7% and ~11% survival). We explore in further detail which trends a real culture could and could not produce until now. Finally we demonstrate brief bipedal stepping on a full size humanoid H1-2.

## Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience

DevFeed: [Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience](<https://devfeed.tech/articles/awaken-hi-scaling-humanoid-intelligence-with-whole-body-human-experience-145669.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26420>)

Author: EngineAI

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoid-robotics](<https://devfeed.tech/tags/humanoid-robotics.md>), [law](<https://devfeed.tech/tags/law.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [model](<https://devfeed.tech/tags/model.md>), [motion](<https://devfeed.tech/tags/motion.md>), [people](<https://devfeed.tech/tags/people.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [scale](<https://devfeed.tech/tags/scale.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vision-language-action](<https://devfeed.tech/tags/vision-language-action.md>), [whole-body-motion](<https://devfeed.tech/tags/whole-body-motion.md>)

### AI overview

Awaken-Human pairs about 50,000 hours of egocentric stereo video with synchronized whole-body motion across more than 100 skills. Using this data, Awaken-HI jointly predicts human motion and robot actions through a shared action expert; directly supervising that expert with human trajectories improves transfer to humanoid loco-manipulation. The authors report that more human pretraining data lowers held-out robot action prediction error and raises downstream real-robot success. After full-corpus pretraining and T800 adaptation, the model reaches a 93.75% mean success rate across eight individual tasks, outperforming GR00T N1.7 and π₀.₅ in individual and long-horizon evaluations. It also generalizes to objects not seen during robot post-training and new pairings of familiar objects and destinations.

### Source excerpt

arXiv:2611.26420v1 Announce Type: cross Abstract: A central goal of humanoid robotics is for robots to perform the everyday work people do in homes and workplaces. Existing egocentric video datasets cover many of these activities but provide little synchronized whole-body motion data for learning loco-manipulation at scale. We build Awaken-Human, which pairs approximately 50,000 hours of egocentric stereo video with synchronized whole-body human motion and covers more than 100 skills. Building on this, we also introduce Awaken-HI (Humanoid Intelligence), a vision-language-action model for humanoid loco-manipulation that jointly predicts original human motion and retargeted robot actions through a shared action expert. We show that loco-manipulation skills transfer more effectively from people to humanoids when human trajectories directly supervise the shared action expert. Increasing human pretraining data reduces held-out robot action prediction error according to an empirical scaling law and raises the mean success rate on downstream real-robot tasks. After full-corpus pretraining and T800 adaptation, Awaken-HI achieves a mean success rate of 93.75% across eight individual tasks and outperforms GR00T N1.7 and $\pi_{0.5}$ in both individual and long-horizon evaluations. The same policy generalizes to objects unseen during robot post-training and to new pairings of familiar objects and destinations.

## Disney's new Star Wars robots use AI to react to guests in real time, but can't go off-script

DevFeed: [Disney's new Star Wars robots use AI to react to guests in real time, but can't go off-script](<https://devfeed.tech/articles/disney-s-new-star-wars-robots-use-ai-to-react-to-guests-in-real-time-but-can-t-go-off-script-143632.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114620-disney-new-star-wars-robots-use-ai-react.html>)

Author: Skye Jacobs

Published: 2026-11-19T14:04:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [The Three Main Cloud Service Models](<https://devfeed.tech/topics/the-three-main-cloud-service-models.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aliens](<https://devfeed.tech/tags/aliens.md>), [amazon-aws](<https://devfeed.tech/tags/amazon-aws.md>), [animatronic](<https://devfeed.tech/tags/animatronic.md>), [animatronics](<https://devfeed.tech/tags/animatronics.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cloud](<https://devfeed.tech/tags/aws-cloud.md>), [aws-re-invent](<https://devfeed.tech/tags/aws-re-invent.md>), [camera](<https://devfeed.tech/tags/camera.md>), [compute](<https://devfeed.tech/tags/compute.md>), [conference](<https://devfeed.tech/tags/conference.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-model](<https://devfeed.tech/tags/decision-model.md>), [disney](<https://devfeed.tech/tags/disney.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [guests](<https://devfeed.tech/tags/guests.md>), [park](<https://devfeed.tech/tags/park.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [robots](<https://devfeed.tech/tags/robots.md>), [script](<https://devfeed.tech/tags/script.md>), [star-wars](<https://devfeed.tech/tags/star-wars.md>), [tech-culture](<https://devfeed.tech/tags/tech-culture.md>), [the-mandalorian](<https://devfeed.tech/tags/the-mandalorian.md>)

### AI overview

Disney's three Anzellan robots use cameras and microphones to react to guests and one another, while staying within material approved by Imagineers. AWS cloud models divide the work: a fast model handles immediate reactions such as eye contact, while larger models plan slower exchanges using more context. The system selects prerecorded dialogue and designed animations; it does not generate new speech or motion. This preserves creative control and keeps responses predictable, though whether reactions feel immediate in a noisy crowd remains to be tested. The robots are due to appear at AWS re:Invent, and Disney has not committed to a theme park debut.

### Source excerpt

The characters are named Vilo Vele, Kado Bre'a and Jibu Bre'a. Their first public appearance will be at AWS re:Invent in Las Vegas later this month, where conference attendees can interact with them. Disney has not committed to a park debut. However, the characters and the technology behind them could... Read Entire Article

## Robots can do backflips but can't hold a gaze or press piano keys, and scientists think they've fixed that

DevFeed: [Robots can do backflips but can't hold a gaze or press piano keys, and scientists think they've fixed that](<https://devfeed.tech/articles/robots-can-do-backflips-but-can-t-hold-a-gaze-or-press-piano-keys-and-scientists-think-they-ve-fixed-that-143166.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114610-robots-can-do-backflips-but-cant-hold-gaze.html>)

Author: Skye Jacobs

Published: 2026-11-19T11:51:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [easy](<https://devfeed.tech/tags/easy.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [explore](<https://devfeed.tech/tags/explore.md>), [eye](<https://devfeed.tech/tags/eye.md>), [eyeballs](<https://devfeed.tech/tags/eyeballs.md>), [eyes](<https://devfeed.tech/tags/eyes.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [fiber](<https://devfeed.tech/tags/fiber.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [folding](<https://devfeed.tech/tags/folding.md>), [gauge](<https://devfeed.tech/tags/gauge.md>), [graphene](<https://devfeed.tech/tags/graphene.md>), [groups](<https://devfeed.tech/tags/groups.md>), [hand](<https://devfeed.tech/tags/hand.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [materials](<https://devfeed.tech/tags/materials.md>), [muscular](<https://devfeed.tech/tags/muscular.md>), [research](<https://devfeed.tech/tags/research.md>), [robots](<https://devfeed.tech/tags/robots.md>), [science](<https://devfeed.tech/tags/science.md>)

### AI overview

University of Pennsylvania engineers built a soft artificial muscle fiber that can hold a precise position by sensing its own temperature and correcting heat loss. A liquid crystal elastomer contracts when heated, graphene makes it softer and tougher, and an embedded copper coil serves as both heater and temperature-feedback sensor. The system adjusts heating in real time to counter the fiber's tendency to cool and drift back, without a separate sensor. In lab demonstrations, a robot hand varied the force and speed of piano-key presses, while paired fibers moved robotic eyes with controlled, repeatable gaze. The hand was not a skilled pianist. The researchers' next step is combining many fibers into larger systems; coordinating them with AI computer vision is a longer-term goal.

### Source excerpt

The work, published in Advanced Functional Materials, is modeled on the small muscles that move human fingers and eyes. Those muscles make fine, controlled movements, and that kind of control has been hard to get from the hardware inside most robots today. Read Entire Article

## Meet the Anzellans: Inside Imagineering R&D's newest robotic characters

DevFeed: [Meet the Anzellans: Inside Imagineering R&D's newest robotic characters](<https://devfeed.tech/articles/meet-the-anzellans-inside-imagineering-r-d-s-newest-robotic-characters-143691.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/media/meet-the-anzellans-inside-imagineering-rds-newest-robotic-characters/>)

Author: Ari Entin

Published: 2026-11-18T20:03:05Z

Content type: news

Language: en

Sources: [AWS for M&E Blog](<https://devfeed.tech/sources/aws-for-m-e-blog.md>)

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [animations](<https://devfeed.tech/tags/animations.md>), [animatronics](<https://devfeed.tech/tags/animatronics.md>), [audio](<https://devfeed.tech/tags/audio.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-re-invent](<https://devfeed.tech/tags/aws-re-invent.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [disney](<https://devfeed.tech/tags/disney.md>), [disney-plus](<https://devfeed.tech/tags/disney-plus.md>), [disneyland](<https://devfeed.tech/tags/disneyland.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [english](<https://devfeed.tech/tags/english.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [robotic](<https://devfeed.tech/tags/robotic.md>), [walt-disney-imagineering](<https://devfeed.tech/tags/walt-disney-imagineering.md>)

### AI overview

The Anzellans are Audio-Animatronics prototypes that respond to guests and one another in real time instead of repeating a fixed performance. AWS powers their real-time intelligence: fast-decision models support quick reactions, while larger models weigh context. The system selects prerecorded audio and pairs it with dynamic animations, with components optimized for latency. Imagineers created the dialogue, gestures and personalities, keeping the characters within the designed story. The excerpt describes a prototype and an AWS re:Invent showcase; it does not establish a broader public deployment.

### Source excerpt

Meet the Anzellans -- Vilo Vele, Kado Bre'a, and Jibu Bre'a -- the newest Audio-Animatronics character prototype from Walt Disney Imagineering R&D. Built with AWS, these autonomous characters don't run a fixed loop. They perceive guests in real time, decide how to respond, and act on their own, all within the story Imagineers designed.

## Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration

DevFeed: [Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration](<https://devfeed.tech/articles/heave-ho-decentralized-long-horizon-multi-humanoid-collaboration-141759.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22275>)

Author: Ting-Hsuan Chen, Siheng Zhao, Han Jiang, Qi Pan, Louison Lu, Jiaheng Luo, Henghui Bao, Yiyu Chen, Quan Nguyen, Yue Wang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [communication](<https://devfeed.tech/tags/communication.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [design](<https://devfeed.tech/tags/design.md>), [develop](<https://devfeed.tech/tags/develop.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [follower](<https://devfeed.tech/tags/follower.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoids](<https://devfeed.tech/tags/humanoids.md>), [language](<https://devfeed.tech/tags/language.md>), [leader](<https://devfeed.tech/tags/leader.md>)

### AI overview

Heave-Ho coordinates humanoid teams for long-horizon loco-manipulation without network communication. Its low-level multi-agent post-training adapts a humanoid foundation tracking model to physically coupled interactions, enabling decentralized control from local observations. A vision-language planner and speech-based leader-follower mechanism coordinate higher-level plans and synchronize execution. Trained with two identical robots, the system scales to teams of up to ten and generalizes to heterogeneous teams without retraining. On HH-Bench's 12 tasks, evaluations report that it outperforms baseline methods; real-world experiments demonstrate collaboration across challenging tasks. The supplied abstract does not specify the baselines or evaluation results in detail.

### Source excerpt

arXiv:2611.22275v1 Announce Type: cross Abstract: Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a decentralized framework for long-horizon collaborative multi-humanoid loco-manipulation. At the low level, we develop a multi-agent post-training framework that adapts a humanoid foundation tracking model to physically coupled interactions between humanoids, enabling coordinated decentralized control from local observations alone. At the high level, we train a vision-language planner and design a speech-based leader-follower coordination mechanism to synchronize decentralized execution without network communication. Trained with two identical humanoids, our system scales to teams of up to ten robots and generalizes to heterogeneous teams without retraining. To benchmark these capabilities, we introduce HH-Bench, comprising 12 tasks involving teams of 2 to 10 humanoids, including heterogeneous teams. Systematic evaluations show that Heave-Ho consistently outperforms baseline methods, while real-world experiments demonstrate robust decentralized collaboration across challenging tasks.

## A Pen Plotter to Draw You Up (on) the Wall

DevFeed: [A Pen Plotter to Draw You Up (on) the Wall](<https://devfeed.tech/articles/a-pen-plotter-to-draw-you-up-on-the-wall-139333.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/11/17/a-pen-plotter-to-draw-you-up-on-the-wall/>)

Author: Tyler August

Published: 2026-11-18T00:00:35Z

Content type: article

Language: en

Sources: [Hackaday](<https://devfeed.tech/sources/hackaday.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>)

Tags: [3d-printer-hacks](<https://devfeed.tech/tags/3d-printer-hacks.md>), [drivers](<https://devfeed.tech/tags/drivers.md>), [esp32](<https://devfeed.tech/tags/esp32.md>), [firmware](<https://devfeed.tech/tags/firmware.md>), [fluidnc](<https://devfeed.tech/tags/fluidnc.md>), [gravity](<https://devfeed.tech/tags/gravity.md>), [mural](<https://devfeed.tech/tags/mural.md>), [pen-plotter](<https://devfeed.tech/tags/pen-plotter.md>), [plotter](<https://devfeed.tech/tags/plotter.md>), [stepper](<https://devfeed.tech/tags/stepper.md>), [svg](<https://devfeed.tech/tags/svg.md>), [wifi](<https://devfeed.tech/tags/wifi.md>)

### AI overview

Mural 2.0 is a ceiling-anchored, large-format pen plotter built around a FluidNC ESP32 board, TMC2209 drivers, and two NEMA 17 pancake steppers that pull the machine up a single belt. Its geometry sacrifices about 20% of the area at the edges, while marker life can become a constraint after roughly 500 m of drawing. The WiFi interface estimates path length and processes SVG and raster images using sine-wave squiggles or finite-curve space filling. A pause-and-replace-pen routine is planned for a future firmware version.

### Source excerpt

Back in our day you were told not to draw on the walls; nowadays we have robots for that- like Mural 2.0 by [Nik Ivanov]. If the name doesn't give ...read more

## 750 MHz GigaDevice GD32H7 Cortex-M7 MCU family gets up to 9.5MB Flash, EtherCAT for industrial applications

DevFeed: [750 MHz GigaDevice GD32H7 Cortex-M7 MCU family gets up to 9.5MB Flash, EtherCAT for industrial applications](<https://devfeed.tech/articles/750-mhz-gigadevice-gd32h7-cortex-m7-mcu-family-gets-up-to-9-5mb-flash-ethercat-for-industrial-applications-136720.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/17/750-mhz-gigadevice-gd32h7-cortex-m7-mcu-family-gets-up-to-9-5mb-flash-ethercat-for-industrial-applications/>)

Author: Debashis Das

Published: 2026-11-17T07:53:37Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [Embedded Software Dev](<https://devfeed.tech/topics/embedded-software-dev.md>), [Embedded Systems](<https://devfeed.tech/topics/embedded-systems.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [can-bus](<https://devfeed.tech/tags/can-bus.md>), [can-fd](<https://devfeed.tech/tags/can-fd.md>), [cortex-m7](<https://devfeed.tech/tags/cortex-m7.md>), [development-board](<https://devfeed.tech/tags/development-board.md>), [display](<https://devfeed.tech/tags/display.md>), [ethercat](<https://devfeed.tech/tags/ethercat.md>), [flash](<https://devfeed.tech/tags/flash.md>), [gd32h7](<https://devfeed.tech/tags/gd32h7.md>), [gigadevice](<https://devfeed.tech/tags/gigadevice.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hmi](<https://devfeed.tech/tags/hmi.md>), [humanoid-robots](<https://devfeed.tech/tags/humanoid-robots.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [industrial-automation](<https://devfeed.tech/tags/industrial-automation.md>), [mcu](<https://devfeed.tech/tags/mcu.md>), [mipi](<https://devfeed.tech/tags/mipi.md>), [motion-control](<https://devfeed.tech/tags/motion-control.md>), [motor-control](<https://devfeed.tech/tags/motor-control.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

GigaDevice's new GD32H7 industrial MCU variants pair Cortex-M7 performance up to 750 MHz with up to 9,728KB Flash and 1,152KB SRAM, but features vary by model. The GD32H77R targets compact robotic joints and servo drives, with EtherCAT, Ethernet PHYs, and encoder interfaces; GD32H78D/77D adds MIPI DSI, graphics acceleration, and audio for HMIs; GD32H78E/77E combines EtherCAT and encoder support for motion control; GD32H789/779 targets general automation. Other listed features include math and signal-processing accelerators, CAN-FD, security functions, and IEC 61508 SC3 safety support. GigaDevice lists evaluation boards, demo suites, an IDE, firmware libraries, and safety materials. Samples for the full lineup are planned by January 2027, with mass production scheduled for April 2027.

### Source excerpt

GigaDevice adds new industrial parts to the GD32H7 series of Cortex-M7 MCUs, running at up to 750 MHz. The new lineup includes the GD32H77R for robotic joint control, GD32H78D/77D for industrial HMI applications, GD32H78E/77E for real-time motion control, and GD32H789/779 for general industrial automation. The MCUs feature up to 9728KB of on-chip Flash, 1152KB SRAM including 640KB tightly coupled memory (TCM), and hardware accelerators for mathematical operations and digital signal processing. Depending on the variant, they also integrate a MIPI DSI display interface, an EtherCAT slave controller, industrial encoder interfaces, dual Ethernet, and three CAN-FD controllers. The devices target servo drives, humanoid robots, industrial displays, CNC machines, PLCs, and digital power systems. GigaDevice GD32H7 new-generation industrial MCU specifications: MCU Core - 32-bit ARM Cortex-M7 core Up to 750 MHz (GD32H78D, GD32H78E, GD32H789 only) Up to 600 MHz (GD32H77R, GD32H77D, GD32H77E, GD32H779 only) Up to 3,736 CoreMark GPU - Image Processing Accelerator [...] The post 750 MHz GigaDevice GD32H7 Cortex-M7 MCU family gets up to 9.5MB Flash, EtherCAT for industrial applications appeared first on CNX Software - Embedded Systems News.

## XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a Minute

DevFeed: [XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a Minute](<https://devfeed.tech/articles/xmimic-and-xsoma-learning-humanoid-motion-tracking-and-locomotion-in-under-a-minute-139055.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20452>)

Author: Nico Bohlinger, Jan Peters

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Warp](<https://devfeed.tech/topics/warp.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [h100](<https://devfeed.tech/tags/h100.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [jax](<https://devfeed.tech/tags/jax.md>), [learning](<https://devfeed.tech/tags/learning.md>), [motion](<https://devfeed.tech/tags/motion.md>), [motion-tracking](<https://devfeed.tech/tags/motion-tracking.md>), [mujoco](<https://devfeed.tech/tags/mujoco.md>), [unitree-g1](<https://devfeed.tech/tags/unitree-g1.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

XMimic and XSoma apply SuperMimic's learned robot world model and analytic-gradient policy optimization, while compiling the training loop with JAX and MuJoCo Warp and parallelizing iteration steps across up to four GPUs. For locomotion, XSoma models only robot dynamics and computes other quantities, including foot-level terrain height, exactly; it uses a one-second horizon without a critic. On four H100 GPUs, XMimic tracked all 40 LAFAN1 clips with a Unitree G1 in 0.86 minutes, reported as 3.7x faster than BlinkMimic on one GPU. XSoma reached the FastSAC tracking target used in Holosoma tests in 0.77 minutes, reported as 12.3x faster than FastSAC on one GPU, using one eighth as many environment steps.

### Source excerpt

arXiv:2611.20452v1 Announce Type: cross Abstract: We present XMimic and XSoma, which learn humanoid motion tracking and locomotion on rough terrain in under a minute of training. Both follow SuperMimic, which learns a world model of the robot and optimizes the policy with analytic gradients through short rollouts imagined in this model. Existing implementations of this method do not make use of larger GPUs, as every training iteration is a long chain of small GPU operations that run one after another. XMimic and XSoma therefore shorten this chain and run the steps of every iteration at the same time on up to four GPUs. We compile the complete training loop with JAX, including the MuJoCo Warp simulator. For locomotion, XSoma leaves only the dynamics of the robot to the world model and computes everything else exactly, including the terrain height under the feet. It learns with a horizon of one second and without a critic. On four H100 GPUs, XMimic learns to track all 40 LAFAN1 clips with the Unitree G1 in 0.86 minutes, 3.7 times faster than BlinkMimic on one GPU. XSoma reaches the tracking target that Holosoma's tests set for FastSAC in 0.77 minutes, 12.3 times faster than FastSAC on one GPU, while needing only an eighth of its environment steps.

## Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies

DevFeed: [Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies](<https://devfeed.tech/articles/certify-then-select-viability-aware-runtime-steering-of-frozen-diffusion-policies-138826.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19047>)

Author: Angelo Moroncelli, Loris Roveda

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>)

Tags: [a-safety](<https://devfeed.tech/tags/a-safety.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [actions](<https://devfeed.tech/tags/actions.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [availability](<https://devfeed.tech/tags/availability.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cast](<https://devfeed.tech/tags/cast.md>), [certification](<https://devfeed.tech/tags/certification.md>), [condition](<https://devfeed.tech/tags/condition.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [control](<https://devfeed.tech/tags/control.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [edits](<https://devfeed.tech/tags/edits.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [policies](<https://devfeed.tech/tags/policies.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [select](<https://devfeed.tech/tags/select.md>), [steering](<https://devfeed.tech/tags/steering.md>)

### AI overview

CAST steers frozen diffusion policies by sampling a few action chunks, certifying each against a barrier condition, then choosing the certified chunk ranked highest by a learned value ensemble. The authors say certification makes a step safe regardless of the critic, while selection stays within log N nats of the policy conditioned on feasibility when a certified sample exists; a safety-filter projection can be singular to that feasible policy. Because safe actions now may lead to no safe actions later, CAST-V adds policy-conditioned viability, estimated with a model under a finite-sample guarantee or learned from controller logs (CAST-VL). Across robomimic manipulation, a planar quadrotor, a MuJoCo humanoid and a unicycle, CAST reportedly improves joint task-and-constraint success over an output filter in nearly every setting; viability removes most dead ends missed by one-step certification.

### Source excerpt

arXiv:2611.19047v1 Announce Type: cross Abstract: Diffusion policies, which generate short action sequences by denoising random noise, are a leading way to learn robot skills from demonstrations. Once deployed, they meet constraints the demonstrations never contained, and retraining for each is impractical. A safety filter edits the policy's action to satisfy them, but the edit ignores the task, and a large edit can leave the policy where it cannot continue. We propose CAST (Certified Action Selection at Test time): draw a few action chunks from the frozen policy, certify each with a barrier condition, and execute the certified chunk that a learned value ensemble ranks highest. We prove that a certified step is safe whatever the critic does; that, whenever a certified sample exists, the executed chunk stays within log N nats of the policy conditioned on feasibility, while a safety-filter projection can be singular to it; and that an exact closed-loop identity splits the gain of ranking into availability, spread and the critic's target. Certifying the next chunk is not enough: a generative controller can have safe actions available now and none later. We characterise the safe control authority of a frozen policy under finite sampling, and CAST-V preserves it through a policy-conditioned viability, estimated with a model under a finite-sample guarantee or learned from the controller's own logs (CAST-VL). On robomimic manipulation, a planar quadrotor, a MuJoCo humanoid and a unicycle, with frozen policies, CAST raises joint task-and-constraint success above the output filter in nearly every setting; certifying before ranking is decisive where a filter's edit is large, and viability removes most dead ends that one-step certification cannot see. Project page: https://clmoro.github.io/cast.

## Personalization of Basic and Moral Values Guiding LLM-Controlled Assistant Robots

DevFeed: [Personalization of Basic and Moral Values Guiding LLM-Controlled Assistant Robots](<https://devfeed.tech/articles/personalization-of-basic-and-moral-values-guiding-llm-controlled-assistant-robots-135177.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18230>)

Author: Mateusz Wozniak, Qi Gao, Agnieszka Wykowska

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [robots](<https://devfeed.tech/tags/robots.md>), [values](<https://devfeed.tech/tags/values.md>)

### AI overview

In a study of 22 potential users, participants wanted assistant robots to express lower personal-focus values and higher social-focus values than their own, while desired moral values were nearly identical. Researchers compared the simplified Schwartz Values Survey (SVS), Portrait Values Questionnaire (PVQ-21), and Moral Foundations Questionnaire (MFQ) as personalization tools using UEQ-S, then benchmarked 15 contemporary LLMs against the resulting profiles. Prompting models to act as robots shifted their values only weakly toward the desired profile, suggesting prompts alone did not achieve explicit value personalization. The supplied text is an abstract, so it does not provide detailed instrument comparisons or benchmark results.

### Source excerpt

arXiv:2611.18230v1 Announce Type: cross Abstract: Personal assistant robots powered by large language models (LLMs) are likely to enter everyday life within the next decade, but the values that should guide their behaviour remain largely unspecified. Current alignment practice steers a single model toward an aggregate of human values, ignoring that individual users may prefer a robot whose value profile differs from their own. We administer parallel self- and robot-targeted versions of three established psycho-metric instruments - the simplified Schwartz Values Survey (SVS), the Portrait Values Questionnaire (PVQ-21), and the Moral Foundations Questionnaire (MFQ) - to potential future users (N=22), capturing both their personal values and the values they would want an assistant robot to embody. We compare the three instruments as personalization tools using the UEQ-S and benchmark fifteen contemporary LLMs against the resulting profiles. Participants wanted their robot to score markedly lower than themselves on personal-focus values and higher on social-focus values; moral profiles were nearly identical. LLMs prompted to act as robots shifted only weakly toward the desired profile, indicating that default model behaviour and prompt engineering are no substitute for explicit value personalization.

## X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot

DevFeed: [X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot](<https://devfeed.tech/articles/x-nav-technical-report-real-world-long-horizon-indoor-to-outdoor-navigation-on-a-humanoid-robot-135084.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17598>)

Author: Jiaxin Huang, Chengxing Lin, Xiaoyu Luo, Sirui Chen, Jingyu Guo, Aolin Li, Kairui Chen, Rui Zhen, Cheng Wen, Kerui Gu, Shunyao Wang, Zhihui Peng, Shaoli Huang

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Robot Navigation](<https://devfeed.tech/topics/robot-navigation.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>)

Tags: [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoid-robot](<https://devfeed.tech/tags/humanoid-robot.md>), [lidar](<https://devfeed.tech/tags/lidar.md>), [navigation](<https://devfeed.tech/tags/navigation.md>), [outdoor](<https://devfeed.tech/tags/outdoor.md>), [outdoors](<https://devfeed.tech/tags/outdoors.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [rgb](<https://devfeed.tech/tags/rgb.md>), [route](<https://devfeed.tech/tags/route.md>), [site](<https://devfeed.tech/tags/site.md>)

### AI overview

X-Nav demonstrates a language-instructed, roughly 100-metre indoor-to-outdoor mission on the Lingxi X2 humanoid, from an office lobby to a store in a neighboring building. Its workflow, X-Navarch, breaks a brief instruction into subtasks and deploys MELIOR for target navigation and obstacle avoidance. MELIOR uses the robot's built-in RGB camera and has two variants: MELIOR-A predicts actions, while MELIOR-N predicts a navigation goal. The demonstrated mission included a destination change and passage through a door; with X-Navarch, the robot also avoided static and dynamic obstacles. LiDAR and odometry supported target approach and low-level control. Site-specific adaptation used digital-twin data and improved closed-loop success in the twin before real-site deployment. MELIOR also achieved competitive results on R2R-CE and RxR-CE; the excerpt gives no quantitative benchmark results.

### Source excerpt

arXiv:2611.17598v1 Announce Type: cross Abstract: Long-horizon navigation from indoors to outdoors remains an open problem for humanoid robots: one instruction covers rooms, doors and roads, and the camera moves with the gait. Worken, AGIBOT's measure of productive robot work, depends on robots that reach their workplaces autonomously. We present X-Nav, to our knowledge the first system to take a bipedal humanoid through a language-instructed long-horizon mission from indoors to outdoors. X-Nav covers a pipeline from data to deployment. Its data engine collects navigation data in open-source scenes, in digital twins of deployment sites and on real robots. Its navigation model, MELIOR, takes only RGB images from the robot's built-in camera and comes in two versions: MELIOR-A predicts actions, and MELIOR-N predicts a navigation goal. Its agentic workflow, X-Navarch, turns a brief human instruction into sub-tasks and deploys MELIOR on the robot with explicit target navigation and obstacle avoidance. On the Lingxi X2, X-Nav completes a mission of about a hundred metres from an office lobby to a store in a neighbouring building; LiDAR and odometry are used for target approach and low-level control. The mission is completed with both versions of MELIOR: the robot follows a change of destination and walks through a door from the lobby to the road, and with X-Navarch it also passes static and dynamic obstacles on the route. During deployment, MELIOR is adapted with data collected in a digital twin of the site; the adaptation raises its closed-loop success rate in the twin, and the adapted model is then deployed on the robot at the real site. In addition, MELIOR achieves competitive results on the R2R-CE and RxR-CE benchmarks.

## Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment

DevFeed: [Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment](<https://devfeed.tech/articles/vision-language-action-models-a-life-cycle-survey-of-design-training-and-deployment-135191.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18372>)

Author: Suvarna Kadam (Witsense AI), Soran Parsa (University of Huddersfield)

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Robot Navigation](<https://devfeed.tech/topics/robot-navigation.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>)

Tags: [camera](<https://devfeed.tech/tags/camera.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [models](<https://devfeed.tech/tags/models.md>), [navigation](<https://devfeed.tech/tags/navigation.md>), [survey](<https://devfeed.tech/tags/survey.md>), [training](<https://devfeed.tech/tags/training.md>), [vision-language-action](<https://devfeed.tech/tags/vision-language-action.md>)

### AI overview

The survey traces vision-language-action models from design through training and deployment, reviewing 88 works and analyzing 22 models across seven axes. It reports broader training data--from teleoperated robot data to community episodes and egocentric video--and a split between 3-7 billion-parameter models and newer sub-billion models that run on consumer GPUs. Generalist models are beginning to combine manipulation and navigation. The survey also compares VLAs with world-action models that predict future observations alongside actions, and notes evidence that strong benchmark performance may not hold when objects or cameras shift slightly.

### Source excerpt

arXiv:2611.18372v1 Announce Type: cross Abstract: Vision-language-action (VLA) models adapt web-pretrained vision-language models to output robot actions, so that web knowledge carries over to physical control. In under 4 years the field has moved from RT-2, the first VLA, to open models that fine-tune on a single consumer GPU and to proprietary generalists that clean unseen homes. This survey reviews 88 works from December 2022 to October 2026, mainly on manipulation and navigation, plus humanoid control, world-action models and evaluation. We follow a VLA through its life cycle, from model design to training and deployment, along seven axes. Model design covers (a) inputs and memory, what the model observes; (b) architecture, how its pipeline is built; (c) action output, how it produces motor commands; and (d) intermediate predictions, what else it predicts, from reasoning steps to future observations. Training covers (e) pretraining data, the mix of robot, web, human and simulated data, and (f) post-training, adaptation to the target robot. Deployment covers (g) real-time execution, keeping pace with the robot. We analyse 22 models on these axes and report their training data, model size, inference speed and hardware. Three trends emerge: (i) training data has broadened, from about 10,000 hours of teleoperated robot data ($\pi_0$) to 23,000 community-collected episodes (SmolVLA) and 20,000 hours of egocentric human video (GR00T N1.7); (ii) model sizes have split: most recent models have 3-7 billion parameters, while a new group under one billion runs on consumer GPUs; and (iii) generalist VLAs are emerging that handle both manipulation and navigation, such as UniVLA and Qwen-VLA. We also compare VLAs with world-action models, which predict future observations as well as actions. We review evidence that some VLAs with near-perfect benchmark scores fail when objects or the camera move slightly, and open up further research questions.

## AAEON BOXER-8741AI industrial Edge AI box PC NVIDIA Jetson Thor T5000 with dual 10GbE and four 5GbE LAN

DevFeed: [AAEON BOXER-8741AI industrial Edge AI box PC NVIDIA Jetson Thor T5000 with dual 10GbE and four 5GbE LAN](<https://devfeed.tech/articles/aaeon-boxer-8741ai-industrial-edge-ai-box-pc-nvidia-jetson-thor-t5000-with-dual-10gbe-and-four-5gbe-lan-135369.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/16/aaeon-boxer-8741ai-industrial-edge-ai-box-pc-nvidia-jetson-thor-t5000-with-dual-10gbe-and-four-5gbe-lan/>)

Author: Debashis Das

Published: 2026-11-16T04:00:27Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [Thor](<https://devfeed.tech/topics/thor.md>), [Jetson](<https://devfeed.tech/topics/jetson.md>), [Isaac](<https://devfeed.tech/topics/isaac.md>), [Holoscan](<https://devfeed.tech/topics/holoscan.md>), [Metropolis](<https://devfeed.tech/topics/metropolis.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [10 Gigabit Ethernet](<https://devfeed.tech/topics/10gbe-networking.md>)

Tags: [10gbe](<https://devfeed.tech/tags/10gbe.md>), [128gb-lpddr5x](<https://devfeed.tech/tags/128gb-lpddr5x.md>), [2-5gbe](<https://devfeed.tech/tags/2-5gbe.md>), [4g](<https://devfeed.tech/tags/4g.md>), [5g](<https://devfeed.tech/tags/5g.md>), [aaeon](<https://devfeed.tech/tags/aaeon.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-performance](<https://devfeed.tech/tags/ai-performance.md>), [applications](<https://devfeed.tech/tags/applications.md>), [arm](<https://devfeed.tech/tags/arm.md>), [artificial-intelligence-ai](<https://devfeed.tech/tags/artificial-intelligence-ai.md>), [automotive](<https://devfeed.tech/tags/automotive.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [box](<https://devfeed.tech/tags/box.md>), [can-bus](<https://devfeed.tech/tags/can-bus.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [jetson](<https://devfeed.tech/tags/jetson.md>), [jetson-thor](<https://devfeed.tech/tags/jetson-thor.md>), [lan](<https://devfeed.tech/tags/lan.md>), [linux](<https://devfeed.tech/tags/linux.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-jetson](<https://devfeed.tech/tags/nvidia-jetson.md>), [pc](<https://devfeed.tech/tags/pc.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [rs485](<https://devfeed.tech/tags/rs485.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [ubuntu](<https://devfeed.tech/tags/ubuntu.md>)

### AI overview

AAEON's BOXER-8741AI is a Jetson Thor T5000 industrial edge computer aimed at robotics and multi-sensor workloads. It is specified with 128GB LPDDR5X memory and up to 2070 sparse FP4 TFLOPS, plus two 10GbE and four 5GbE ports, two CAN FD interfaces, RS-232/RS-485, and optional GPIO. M.2 slots support NVMe storage, optional Wi-Fi/Bluetooth, and optional 4G/5G; power input is 19-48V DC, and operating temperature is -20°C to 60°C. The system supports JetPack 7.1 or later and NVIDIA tools including CUDA and TensorRT. The listed configuration includes a 128GB NVMe SSD; the 240W adapter and power cord are separate. The article lists a $10,219 price and expected availability around December 29, 2026, with preorders open at the time of writing.

### Source excerpt

AAEON BOXER-8741AI is an industrial edge AI box PC built around the NVIDIA Jetson Thor T5000 module, delivering up to 2070 FP4 TFLOPS (sparse) of AI performance and featuring 128GB LPDDR5X memory. Designed for humanoid robotics, autonomous mobile robots (AMRs), and multi-sensor perception workloads, it features two 10GbE and four 5GbE ports, two CAN FD interfaces, RS-232/RS-485, optional GPIO, and four USB 3.2 Gen 2 ports. Expansion options include M.2 slots for NVMe storage, Wi-Fi/Bluetooth, and 4G/5G cellular connectivity. The computer supports 19V to 48V DC input and operates from -20°C to 60°C for industrial applications. AAEON BOXER-8741AI specifications: SoM - NVIDIA Jetson Thor T5000 module CPU - 14-core 64-bit ARM Neoverse-V3AE @ up to 2.6GHz GPU - 2560-core NVIDIA Blackwell GPU with 96 fifth-generation Tensor Cores, Multi-Instance GPU (MIG) support with 10 Texture Processing Clusters (TPCs) VPU Video Decode - 4x 8Kp30 (H.265), 10x 4Kp60 (H.265), 22x 4Kp30 (H.265), [...] The post AAEON BOXER-8741AI industrial Edge AI box PC NVIDIA Jetson Thor T5000 with dual 10GbE and four 5GbE LAN appeared first on CNX Software - Embedded Systems News.

## The Future of AI Jobs May Be Outside the Tech Industry

DevFeed: [The Future of AI Jobs May Be Outside the Tech Industry](<https://devfeed.tech/articles/the-future-of-ai-jobs-may-be-outside-the-tech-industry-134598.md>)

Original publisher: [Read original article](<https://hackernoon.com/the-future-of-ai-jobs-may-be-outside-the-tech-industry?source=rss>)

Author: Pavel Yakovlev

Published: 2026-11-15T19:52:16Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agi](<https://devfeed.tech/tags/agi.md>), [agriculture](<https://devfeed.tech/tags/agriculture.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-engineer](<https://devfeed.tech/tags/ai-engineer.md>), [ai-in-production](<https://devfeed.tech/tags/ai-in-production.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-job-market](<https://devfeed.tech/tags/ai-job-market.md>), [ai-labs](<https://devfeed.tech/tags/ai-labs.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [coding](<https://devfeed.tech/tags/coding.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [future](<https://devfeed.tech/tags/future.md>), [future-of-ai](<https://devfeed.tech/tags/future-of-ai.md>), [future-of-software-engineering](<https://devfeed.tech/tags/future-of-software-engineering.md>), [future-of-work-with-ai](<https://devfeed.tech/tags/future-of-work-with-ai.md>), [industrial-ai-adoption](<https://devfeed.tech/tags/industrial-ai-adoption.md>), [industry](<https://devfeed.tech/tags/industry.md>), [jobs](<https://devfeed.tech/tags/jobs.md>), [machine-learning-careers](<https://devfeed.tech/tags/machine-learning-careers.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [software](<https://devfeed.tech/tags/software.md>), [tech](<https://devfeed.tech/tags/tech.md>)

### AI overview

The article predicts that by 2031 AI agents will write most company code while developers shift toward defining problems and reviewing results; US developer employment may grow even as routine coding and some specialties shrink. It expects robots to take on paid warehouse and factory work and robotaxis to expand, while home robots remain niche. AI adoption in less digital industries lags because of poor data, legacy systems, regulation and limited expertise, but the author expects production use to rise, especially in medicine, energy and manufacturing. As a result, the author forecasts more AI engineering roles outside tech, where workers can combine model skills with industry knowledge. The author presents these as predictions, notes uneven adoption and uncertain productivity evidence, and advises learners to build fundamentals, learn to work with agents, and understand real business problems.

### Source excerpt

Five predictions for AI jobs by 2031, exploring software engineering, coding agents, robotics, industrial AI adoption, and future career opportunities.

## Adapt Human Motion for Robots with NVIDIA SOMA Retargeter

DevFeed: [Adapt Human Motion for Robots with NVIDIA SOMA Retargeter](<https://devfeed.tech/articles/adapt-human-motion-for-robots-with-nvidia-soma-retargeter-132446.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/adapt-human-motion-for-robots-with-nvidia-soma-retargeter/>)

Author: John Malaska

Published: 2026-11-13T17:00:00Z

Content type: tutorial

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Isaac](<https://devfeed.tech/topics/isaac.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Isaac Sim](<https://devfeed.tech/topics/isaac-sim.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [actions](<https://devfeed.tech/tags/actions.md>), [actuator](<https://devfeed.tech/tags/actuator.md>), [after](<https://devfeed.tech/tags/after.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agibot](<https://devfeed.tech/tags/agibot.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [great](<https://devfeed.tech/tags/great.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [humanoid-robots](<https://devfeed.tech/tags/humanoid-robots.md>), [isaac-lab](<https://devfeed.tech/tags/isaac-lab.md>), [motion](<https://devfeed.tech/tags/motion.md>), [newton](<https://devfeed.tech/tags/newton.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-research](<https://devfeed.tech/tags/nvidia-research.md>), [offers](<https://devfeed.tech/tags/offers.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [point](<https://devfeed.tech/tags/point.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robotics-simulation](<https://devfeed.tech/tags/robotics-simulation.md>), [robots](<https://devfeed.tech/tags/robots.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [teaching](<https://devfeed.tech/tags/teaching.md>), [timing](<https://devfeed.tech/tags/timing.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [warp](<https://devfeed.tech/tags/warp.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

NVIDIA SOMA Retargeter adapts human motion to a robot's proportions and range of motion, then exports per-frame root poses and joint angles as CSV for downstream training or control. It accepts BVH animation on the SOMA skeleton; motion can come from capture, video reconstruction, or generation, but must be represented compatibly. The viewer supports configuring a robot, retargeting motion through weighted inverse kinematics, and applying post-processing such as foot-plant correction. Sample configurations and reference results cover five humanoid robots. Developers can refine weights on representative motions, then batch-retarget larger collections. For policy training, SONIC includes a SOMA CSV converter for G1, while ProtoMotions provides another physics-based tracking framework; the input representation and policy must match the target robot. The excerpt also describes simulation evaluation and a MicroDuck example, where trained controllers were compared with reference motions.

### Source excerpt

Human motion offers roboticists a great starting point for teaching humanoid robots how to move. A human demonstration captures the coordination and timing...

## EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming

DevFeed: [EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming](<https://devfeed.tech/articles/egox-egocentric-cross-embodiment-manipulation-with-embodiment-dreaming-132278.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16728>)

Author: Yaru Niu, Binghong Chen, Changwei Yao, Shangtao Li, Zhenlong Fang, Revanth Krishna Senthilkumaran, Shuai Zhou, Yuemin Mao, Kalie Ching, Po-Ju Chao, Yudong Luo, Peiqi Yu, Heng Zhang, Hao Zhang, Bingqin

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>)

Tags: [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [dreaming](<https://devfeed.tech/tags/dreaming.md>), [framework](<https://devfeed.tech/tags/framework.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [modular](<https://devfeed.tech/tags/modular.md>), [policies](<https://devfeed.tech/tags/policies.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [progress](<https://devfeed.tech/tags/progress.md>), [raises](<https://devfeed.tech/tags/raises.md>), [robots](<https://devfeed.tech/tags/robots.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

EgoX uses heterogeneous demonstrations from humans, robots, and simulation to improve manipulation policies across embodiments. Its MXT+ model gives each embodiment dedicated tokenizers for observation modalities and experts for action modalities, while sharing a Transformer trunk. During pretraining, an embodiment-dreaming objective predicts latent future visual and proprioceptive states; the model is then fine-tuned on demonstrations for the target embodiment. Across 13 task-embodiment pairs, cross-embodiment pretraining raised average normalized task progress from 0.63 to 0.80 versus training from scratch, and from 0.53 to 0.77 in out-of-distribution conditions. The abstract reports ablation benefits from broader mixtures, modular interfaces, and embodiment dreaming, whose use also yielded more similar latent geometry across embodiments.

### Source excerpt

arXiv:2611.16728v1 Announce Type: cross Abstract: Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce EgoX, an egocentric cross-embodiment learning framework that organizes heterogeneous demonstrations through semantically corresponding observation and action modalities. EgoX pretrains a Modularized Cross-Embodiment Transformer with Embodiment Dreaming (MXT+) on this mixture and fine-tunes it on target-embodiment demonstrations. Within each embodiment, MXT+ assigns a dedicated tokenizer to each observation modality and a dedicated expert to each action modality, with a Transformer trunk shared across embodiments. A training-only embodiment-dreaming objective predicts latent representations of future visual and proprioceptive states, encouraging the shared trunk to model each embodiment's dynamics. Across 13 task-embodiment pairs spanning five tasks and six robot embodiments, including five physical robots and one simulated humanoid, cross-embodiment pretraining raises MXT+'s average normalized task progress from 0.63 to 0.80 over training from scratch. The gains are particularly pronounced under out-of-distribution conditions, where average task progress increases from 0.53 to 0.77. Ablations demonstrate the benefits of broader pretraining mixtures, modular interfaces, and embodiment dreaming, with dreaming producing more similar latent geometry across embodiments. Project page: egox-dream.github.io.

## BlinkMimic: Training a Humanoid Motion Tracker in Minutes on a Single GPU

DevFeed: [BlinkMimic: Training a Humanoid Motion Tracker in Minutes on a Single GPU](<https://devfeed.tech/articles/blinkmimic-training-a-humanoid-motion-tracker-in-minutes-on-a-single-gpu-133118.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16422>)

Author: Fuyi Chen

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [World models](<https://devfeed.tech/topics/world-models.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [added](<https://devfeed.tech/tags/added.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [body](<https://devfeed.tech/tags/body.md>), [build](<https://devfeed.tech/tags/build.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [capture](<https://devfeed.tech/tags/capture.md>), [cases](<https://devfeed.tech/tags/cases.md>), [clip](<https://devfeed.tech/tags/clip.md>), [code](<https://devfeed.tech/tags/code.md>), [component](<https://devfeed.tech/tags/component.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [minutes](<https://devfeed.tech/tags/minutes.md>), [motion](<https://devfeed.tech/tags/motion.md>), [tracker](<https://devfeed.tech/tags/tracker.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

BlinkMimic trains one policy for 40 LAFAN1 motion clips on a simulated Unitree G1 in 3.4 minutes on a single RTX 4090, averaged over three seeds. The reported stopping point requires three consecutive checkpoints with normalized return of at least 0.82 and no failed clip. Building on SuperMimic and InstantTrack, it combines a step size that decreases later in training, resets triggered by deployed-policy failures under deployment conditions, and GPU graph capture of the full iteration. The authors divide training time into iteration cost, iterations to fit motions, and iterations to eliminate remaining failures; leave-one-out ablations and measurements attribute component effects to these terms. The result is limited to the stated simulated setup and success criterion.

### Source excerpt

arXiv:2611.16422v1 Announce Type: cross Abstract: Whole-body motion tracking lets a humanoid robot follow reference motions, but training a tracking policy for a library of motions has usually taken hours of GPU time. SuperMimic showed that the policy can instead be trained by backpropagating through a world model learned from parallel simulation, and InstantTrack added Muon updates, a residual policy around the reference and an averaged deployed policy. We build on both and present BlinkMimic, a recipe that makes this training faster. On a simulated Unitree G1, BlinkMimic trains one policy for all 40 LAFAN1 clips in 3.4 minutes on a single RTX 4090, measured until three consecutive checkpoints reach a normalized return of at least 0.82 with no failed clip (mean of three seeds). We split training time into the cost of an iteration, the iterations needed to fit the motions, and the iterations needed to remove the last failures, and assign each component, inherited or new, to one of these terms. The new components are a step size that decreases once training has progressed, resets directed by failures of the deployed policy under deployment conditions, and GPU graph capture of the whole iteration. A leave-one-out ablation with three seeds per component shows which term each component affects, and further measurements of the gradient, the update rule and the failure cases explain these effects. Code and per-seed results are available at https://github.com/fuyichen0725/blinkmimic.

## Robots That Talk Too Much and Don't Listen Enough

DevFeed: [Robots That Talk Too Much and Don't Listen Enough](<https://devfeed.tech/articles/robots-that-talk-too-much-and-don-t-listen-enough-132240.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16473>)

Author: Graham Wilcock, Kristiina Jokinen

Published: 2026-11-13T05:00:00Z

Content type: opinion

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [voice ai](<https://devfeed.tech/topics/voice-ai.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [failures](<https://devfeed.tech/tags/failures.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robots](<https://devfeed.tech/tags/robots.md>), [social-robots](<https://devfeed.tech/tags/social-robots.md>), [speech](<https://devfeed.tech/tags/speech.md>), [speech-recognition](<https://devfeed.tech/tags/speech-recognition.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

The paper argues that better speech recognition has improved spoken interaction with social robots, but turn-taking failures and other misunderstandings remain common. It reviews earlier approaches to speech recognition and turn-taking, then proposes multimodal bidirectional streaming as a way to reduce turn-taking failures. The excerpt does not specify implementation details or report comparative results.

### Source excerpt

arXiv:2611.16473v1 Announce Type: cross Abstract: Until recently, the biggest obstacles to natural spoken interaction with social robots were speech recognition errors and turn-taking failures. Advances in speech recognition have enabled much better spoken interaction, but turn-taking failures and other misunderstandings continue to be far too prevalent. This short paper looks back at earlier methods for improving speech recognition and turn-taking in interaction with social robots, and then looks at what can be done today, arguing that multimodal bidirectional streaming is needed to reduce the frequency of turn-taking failures.

## CFGComposer: Compositional Audio-Text-to-Motion Generation via Copula Score Correction

DevFeed: [CFGComposer: Compositional Audio-Text-to-Motion Generation via Copula Score Correction](<https://devfeed.tech/articles/cfgcomposer-compositional-audio-text-to-motion-generation-via-copula-score-correction-132095.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15101>)

Author: Pengyang Shi, Jinlu Zhang, Chunze Lin, Yizhou Wang, Li Yi

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [all](<https://devfeed.tech/tags/all.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [audio](<https://devfeed.tech/tags/audio.md>), [bias](<https://devfeed.tech/tags/bias.md>), [blending](<https://devfeed.tech/tags/blending.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-sd](<https://devfeed.tech/tags/cs-sd.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [embodied-ai](<https://devfeed.tech/tags/embodied-ai.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [g1](<https://devfeed.tech/tags/g1.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gestures](<https://devfeed.tech/tags/gestures.md>), [humanoid](<https://devfeed.tech/tags/humanoid.md>), [motion](<https://devfeed.tech/tags/motion.md>), [text](<https://devfeed.tech/tags/text.md>)

### AI overview

CFGComposer generates whole-body motion conditioned on speech audio and text by estimating the cross-modal copula score that naive epsilon blending of independently trained diffusion models omits. It injects this score as an epsilon-space correction, using a jointly trained model and a classifier-free-guidance analogy. On BEAT, the authors report semantic fidelity of SRGR 0.9916 and FID 27.18, beat alignment of 0.1826 versus 0.1743 for ground truth, and 76-83% wins in blind pairwise human evaluations against prior methods. They also report direct sim-to-real transfer in deployment on a Unitree G1 humanoid.

### Source excerpt

arXiv:2611.15101v1 Announce Type: cross Abstract: Generating whole-body gestures that are simultaneously rhythmically synchronized with speech audio and semantically aligned with text descriptions is a fundamental challenge in embodied AI and social robotics. We tackle this Audio-Text-to-Motion (AT2M) problem by composing two independently-trained diffusion models at inference time and refine bias in joint inference by modeling the copula score $s_I$. A rigorous theoretical analysis reveals that naive epsilon blending corresponds to a Product-of-Experts formulation that omits the copula score $s_I$: the cross-modal interaction between audio and text that neither marginal model can capture. We propose CFGComposer: a jointly-trained AT2M diffusion model that estimates $s_I$ via a CFG analogy and injects it as an $\epsilon$-space correction. Experiments on BEAT demonstrate best-in-class semantic fidelity (SRGR $0.9916$, FID $27.18$) with GT-level beat alignment (BA $0.1826$ vs. GT $0.1743$), and 76-83% win rate in blind pairwise human evaluation against all prior methods. Physical deployment on a Unitree G1 humanoid confirms direct sim-to-real transfer.

## Agile Robots raises $500M funding led by SoftBank at $8.5B valuation

DevFeed: [Agile Robots raises $500M funding led by SoftBank at $8.5B valuation](<https://devfeed.tech/articles/agile-robots-raises-500m-funding-led-by-softbank-at-8-5b-valuation-130575.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/12/agile-robots-raises-500m-funding-led-by-softbank-at-8-5b-valuation/>)

Author: Kyt Dotson

Published: 2026-11-12T16:10:57Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Isaac](<https://devfeed.tech/topics/isaac.md>)

Tags: [agile-robots](<https://devfeed.tech/tags/agile-robots.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [emerging-tech](<https://devfeed.tech/tags/emerging-tech.md>), [funding](<https://devfeed.tech/tags/funding.md>), [news](<https://devfeed.tech/tags/news.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [softbank](<https://devfeed.tech/tags/softbank.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-6](<https://devfeed.tech/tags/top-story-6.md>)

### AI overview

Agile Robots raised $500 million in a SoftBank-led Series F at an $8.5 billion valuation, bringing total capital invested to $2 billion. Nvidia, Hitachi and T Capital also participated. The company combines robotic hardware, sensing, computer vision and AI, with force-sensitive manipulation as a core capability. Its products include the Diana 7 arm and Agile One humanoid platforms; the Agile One SN is preconfigured for Nvidia Isaac GR00T models. Agile says the funding will support U.S. expansion, engineering hires, application development and increased production. Its Fürstenfeldbruck facility, opened in early 2026, is described as capable of producing up to 10,000 legged and wheeled humanoid robots annually. The excerpt also reports around 20,000 industrial robotic solutions deployed.

### Source excerpt

German artificial intelligence robotics startup Agile Robots SE announced today that it raised $500 million in new funding at an $8.5 billion valuation. Japanese multinational investment holding company SoftBank led the Series F funding round. Other participants included AI chip leader Nvidia, Japanese group Hitachi and T Capital. According to the company, the financing brings [...] The post Agile Robots raises $500M funding led by SoftBank at $8.5B valuation appeared first on SiliconANGLE.

[Next page](<https://devfeed.tech/topics/humanoid-robots.md?cursor=WyIyMDI2LTExLTEyVDE2OjEwOjU3KzAwOjAwIiwgIjNkYmU0MDg1LTU2MTMtNDYwZi1hZWVkLWM5ZmMyOTY5NGFjNyJd>)