# Laboratory for Information and Decision Systems (LIDS) Published articles for Laboratory for Information and Decision Systems (LIDS). This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Clearing up a robot's fuzzy memory DevFeed: [Clearing up a robot's fuzzy memory]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-11-05T05:00:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Robot Manipulation](), [Image]() Tags: [aeronautical-and-astronautical-engineering](), [algorithms](), [artificial-intelligence](), [computer-science-and-technology](), [computer-vision](), [electrical-engineering-and-computer-science-eecs](), [environment](), [harry-zhang](), [laboratory-for-information-and-decision-systems-lids](), [luca-carlone](), [machine-learning](), [memory](), [mit-schwarzman-college-of-computing](), [nicolas-gorlo](), [object](), [research](), [robot](), [robotics](), [school-of-engineering](), [spatio-temporal-memory](), [system](), [u-s-armed-forces](), [uncertainty-quantification](), [vision-language-models]() ### AI overview UQ-DAAAM helps a robot detect and correct unreliable object descriptions in its map-based memory. It combines the vision-language model's confidence in a caption with its consistency against descriptions from other viewpoints. When uncertainty crosses a threshold, a heuristic selects useful additional views without rerunning the vision-language model; a language model then combines captions, favoring newer and less ambiguous ones. The researchers report that this resolves ambiguities for about 92% of objects using two additional captions per object, raises description accuracy by 5% over the state of the art, and improves answers about objects, locations, and when they were seen compared with baseline methods. The excerpt describes planned extensions to other robots and uncertainty-guided revisits; it does not report those as completed. ### Source excerpt A new system identifies and corrects unreliable object descriptions stored in a robot's memory, improving the robot's ability to interact with its environment. ## MIT affiliates named 2026 Schmidt Sciences AI2050 Fellows DevFeed: [MIT affiliates named 2026 Schmidt Sciences AI2050 Fellows]() Original publisher: [Read original article]() Author: Amanda Moore | Jane Halpern | MIT Laboratory for Information and Decision Systems | Department of Electrical Engineering and Computer Science Published: 2026-10-30T20:15:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [AI Research](), [Artificial Intelligence](), [AI for science](), [Electrical engineering and computer science (EECS)](), [Operations research and optimization]() Tags: [2026](), [abdul-latif-jameel-poverty-action-lab-j-pal](), [affiliates](), [ai](), [alex-damian](), [allison-z-koenecke](), [alumni](), [alumni-ae](), [artificial-intelligence](), [awards-honors-and-fellowships](), [bailey-flanigan](), [beneficial-ai](), [biology](), [computer-science-and-technology](), [economics](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [fellowships](), [hard-problems-in-ai](), [irene-chen](), [juan-carlos-perdomo](), [laboratory-for-information-and-decision-systems-lids](), [manish-raghavan](), [mathematics](), [mit](), [mit-alumni-awards](), [mit-eecs](), [mit-faculty-awards](), [mit-lids](), [mit-schwarzman-college-of-computing](), [mit-sloan-school-of-management](), [political-science](), [research](), [schmidt-sciences-ai2050-fellows](), [school-of-engineering](), [school-of-humanities-arts-and-social-sciences](), [school-of-science](), [sendhil-mullainathan](), [yunha-hwang]() ### AI overview Five MIT faculty members, two alumni and a former postdoc were named 2026 AI2050 Fellows by Schmidt Sciences. The excerpt details five faculty projects: Sendhil Mullainathan will study how AI-detectable patterns can be translated into testable theories; Alex Damian will focus on effective AI model training; Bailey Flanigan on gathering structured public input for lawmakers; Yunha Hwang on determining biological enzyme functions; and Manish Raghavan on reducing harms and strengthening benefits as AI reliance spreads. AI2050 frames the work around the question of how AI could be made hugely beneficial to society by 2050. The excerpt names alumni Irene Chen and Allison Z. Koenecke and former postdoc Juan Carlos Perdomo as additional Early Career Fellows, but does not describe their projects. ### Source excerpt Five MIT faculty members and two additional alumni are honored with fellowships to advance research on beneficial AI. ## Q&A: Hey AI, who should I vote for this year? DevFeed: [Q&A: Hey AI, who should I vote for this year?]() Original publisher: [Read original article]() Author: Abby Abazorius | MIT News Published: 2026-10-30T19:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [AI Chat](), [Artificial Intelligence]() Tags: [2026](), [2026-midterm-elections](), [adam-berinsky](), [ai](), [ai-and-elections](), [ai-chatbots](), [ai-responses](), [ai-systems](), [artificial-intelligence](), [audit](), [auditing](), [chara-podimata](), [charles-steward](), [chatbots](), [computer-science-and-technology](), [data](), [discuss](), [elections](), [interview](), [laboratory-for-information-and-decision-systems-lids](), [llm-election-observatory](), [midterm](), [mit](), [mit-schwarzman-college-of-computing](), [mit-sloan-school-of-management](), [political-science](), [project](), [q-a](), [questions](), [research](), [school-of-humanities-arts-and-social-sciences](), [technology-and-society](), [vote](), [voting-and-elections]() ### AI overview MIT's LLM Election Observatory repeatedly asks popular chatbots a fixed set of election questions, varying user identities and prompt framing, to document how answers, tone, and cited sources change over time. The team plans to share the collected data and preliminary analyses publicly so researchers and voters can examine these otherwise private information environments. Early 2026 observations show differences in presentation, sources, and tone across user identities, sometimes despite the same underlying facts. The researchers have not completed their longitudinal analysis and cannot yet say how stable these differences are or how people respond to them. They caution that confident chatbot answers may be inaccurate, incomplete, or based on weak sources, and recommend treating them as a starting point. Their aim is to audit effects without assuming AI is inherently good or bad for elections. ### Source excerpt MIT professors Adam Berinsky and Chara Podimata discuss a new project to track how AI chatbots are responding to questions about the 2026 U.S. midterm elections. ## Q&A: How AI came to model the "messy" human mind DevFeed: [Q&A: How AI came to model the "messy" human mind]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-10-23T04:00:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [Neural Network](), [Machine learning](), [Language models]() Tags: [ai](), [ai-hallucinations](), [ai-systems](), [algorithms](), [anthropic](), [artificial-intelligence](), [artificial-neural-networks](), [benjamin-lindquist](), [brain](), [chatbot](), [chatgpt](), [claude](), [cognitive-science](), [computer-science-and-technology](), [creative-thinking](), [creativity](), [data](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [generative-ai](), [hallucinations](), [history](), [history-of-ai](), [history-of-science](), [interview](), [laboratory-for-information-and-decision-systems-lids](), [machine-learning](), [messy](), [mind](), [mit-schwarzman-college-of-computing](), [randomness](), [research](), [school-of-engineering](), [school-of-humanities-arts-and-social-sciences](), [technology-and-society]() ### AI overview Lindquist argues that early neural-network researchers deliberately used randomness to produce unexpected outputs they associated with creative thought, while symbolic AI focused on encoding rules and facts. Neural networks gained traction in the 1950s, later shifted toward cognitive science, and grew more powerful as data and computing increased; around 2012 they began outperforming a statistical form of machine learning. Lindquist connects their capacity for surprising conclusions with errors and hallucinations. Today, he says, legal and financial concerns have encouraged companies to suppress strangeness in chatbots. His historical takeaway is that reducing unwanted outputs may also limit creativity and predictability cannot be optimized without tradeoffs. ### Source excerpt Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate. ## Computational tools for society's most complex challenges DevFeed: [Computational tools for society's most complex challenges]() Original publisher: [Read original article]() Author: Michaela Jarvis | MIT Laboratory for Information and Decision Systems Published: 2026-10-02T19:30:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Complex Systems](), [Reinforcement learning](), [Combinatorial optimization](), [Artificial Intelligence](), [Test-driven development]() Tags: [ai-in-transportation](), [algorithms](), [artificial-intelligence](), [autonomous-vehicles](), [cathy-wu](), [civil-and-environmental-engineering](), [complex-systems](), [computer-science-and-technology](), [contextual-rl](), [daniela-rus](), [democratic-decision-making](), [electrical-engineering-and-computer-science-eecs](), [engineering](), [faculty](), [hard-optimization-problems](), [idss](), [laboratory-for-information-and-decision-systems-lids](), [logistics](), [machine-learning](), [mit-cee](), [mit-faculty-profile](), [mit-idss](), [mit-lids](), [mit-schwarzman-college-of-computing](), [profile](), [reinforcement-learning](), [robotaxis](), [robotics](), [school-of-engineering](), [supply-chains](), [technology-and-society](), [traffic-management](), [transportation]() ### AI overview MIT professor Cathy Wu's research applies reinforcement learning and optimization to transportation challenges and other complex systems. Her group developed a way to select problems where reinforcement learning trains and generalizes well, improving training efficiency by up to 30 times. Her later work uses reinforcement learning to study traffic measures with potential emissions reductions and policy implications. ### Source excerpt Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems. ## This game-playing AI is the new champ at Stratego DevFeed: [This game-playing AI is the new champ at Stratego]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-09-30T15:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [machine learning overfitting](), [decision-making](), [Electrical engineering and computer science (EECS)]() Tags: [ai](), [algorithms](), [artificial-intelligence](), [computer-science](), [computer-science-and-technology](), [decision-time-planning](), [electrical-engineering-and-computer-science-eecs](), [engineering](), [gabriele-farina](), [game](), [game-theory](), [google-deepmind](), [human-computer-interaction](), [imperfect-information](), [laboratory-for-information-and-decision-systems-lids](), [machine-learning](), [military](), [mit-schwarzman-college-of-computing](), [national-science-foundation-nsf](), [research](), [samuel-sokota](), [school-of-engineering](), [stanford](), [stratego]() ### AI overview Researchers developed a machine-learning system that defeated top-ranked human Stratego players and outperformed other models while requiring less training computation. The system also performed well in other strategic games and could potentially support decision-making in settings with hidden information, such as military maneuvers, business negotiations, and cybersecurity. ### Source excerpt Able to defeat top-ranked human players and more efficient than other models, the new system could help decision-makers in military maneuvers or business negotiations. ## The effects of an "algorithmic monoculture" depend on the details DevFeed: [The effects of an "algorithmic monoculture" depend on the details]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-09-29T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Computing](), [ai alignment]() Tags: [ai](), [algorithmic-monoculture](), [algorithms](), [artificial-intelligence](), [brian-hedden](), [business-and-management](), [computer-science-and-technology](), [electrical-engineering-and-computer-science-eecs](), [hiring-algorithms](), [human-computer-interaction](), [labor-and-jobs](), [laboratory-for-information-and-decision-systems-lids](), [linguistics](), [machine-learning](), [manish-raghavan](), [mit-schwarzman-college-of-computing](), [mit-sloan-school-of-management](), [philosophy](), [research](), [school-of-engineering](), [school-of-humanities-arts-and-social-sciences]() ### AI overview MIT researchers argue that algorithmic monoculture's effects depend on the domain and algorithm accuracy. Their analysis identifies informational echo chambers that can hinder exploration, while finding that ensembles of hiring algorithms can sometimes overcome this limitation and perform as well as or better than systems using different algorithms. ### Source excerpt In a study focusing on hiring decisions, MIT researchers found the use of a single algorithm by many firms could benefit job seekers in certain situations. ## MIT researchers develop a generative AI method for enforcing hard constraints in safety-critical applications DevFeed: [MIT researchers develop a generative AI method for enforcing hard constraints in safety-critical applications]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-09-14T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Generative AI](), [AI Models](), [Algorithms](), [Requirements](), [Computer vision](), [Robotics]() Tags: [ai](), [ai-models](), [algorithm](), [algorithms](), [artificial-intelligence](), [computer-science-and-technology](), [computer-vision](), [diffusion-models](), [electrical-engineering-and-computer-science-eecs](), [flow-matching](), [generative-ai](), [hard-constrained-sampling](), [hardflow](), [idss](), [kaveh-alim](), [laboratory-for-information-and-decision-systems-lids](), [machine-learning](), [mechanical-engineering](), [mit-schwarzman-college-of-computing](), [navid-azizan](), [optimal-control](), [paper](), [requirements](), [research](), [robotics](), [safe-ai](), [school-of-engineering](), [trajectory-optimization](), [zeyang-li]() ### AI overview MIT researchers developed a deployment-time technique that lets pretrained generative AI models explore solutions while enforcing hard constraints on final outputs. Experiments in robotics, physical-process control, and computer vision found that the method satisfied required constraints and identified better solutions than existing techniques. ### Source excerpt The "HardFlow" algorithm could help generative AI models produce high-quality outputs that obey strict requirements when "pretty close" doesn't cut it. ## The benefits of medical AI assistance vary based on user expertise DevFeed: [The benefits of medical AI assistance vary based on user expertise]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-08-04T09:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [Human-AI evaluation](), [AI Development](), [AI Chat]() Tags: [ai](), [artificial-intelligence](), [bias](), [computer-science-and-technology](), [decision-making](), [dermatological-diagnosis](), [diagnosing-skin-disease](), [diagnostics](), [electrical-engineering-and-computer-science-eecs](), [explainability](), [explainable-ai](), [health-care](), [human-computer-interaction](), [institute-for-medical-engineering-and-science-imes](), [jameel-clinic](), [laboratory-for-information-and-decision-systems-lids](), [large-language-model](), [machine-learning](), [marzyeh-ghassemi](), [medicine](), [research](), [technology-and-society](), [users]() ### AI overview A study found that AI assistance improved skin-disease diagnosis for non-experts and clinicians, but explainability affected users differently. Non-experts often deferred to LLM-based explanations even when the AI was wrong, while clinicians performed best with the model's prediction alone. ### Source excerpt Study finds non-experts deferred to LLM-based diagnostic assistance, even when it was wrong, while clinicians caught AI errors. ## Alexander Rakhlin named director of the MIT Statistics and Data Science Center DevFeed: [Alexander Rakhlin named director of the MIT Statistics and Data Science Center]() Original publisher: [Read original article]() Author: Institute for Data, Systems, and Society Published: 2026-08-03T19:50:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Statistics](), [Data Science](), [Machine learning]() Tags: [ai-in-statistics](), [alexander-sasha-rakhlin](), [alumni-ae](), [ankur-moitra](), [artificial-intelligence](), [brain-and-cognitive-sciences](), [computer-science-and-technology](), [data-science](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [fotini-christia](), [idss](), [laboratory-for-information-and-decision-systems-lids](), [leadership](), [lids](), [machine-learning](), [mit-bcs](), [mit-faculty-appointments](), [mit-idss](), [mit-leadership](), [mit-schwarzman-college-of-computing](), [mit-statistics-and-data-science-center-sdsc](), [philippe-rigollet](), [richard-dick-larson](), [school-of-engineering](), [school-of-science](), [statistics]() ### AI overview Alexander Rakhlin has been named the next director of MIT's Statistics and Data Science Center, succeeding Ankur Moitra. Rakhlin has been affiliated with the center since 2016 and has led its interdisciplinary doctoral program, overseeing more than 75 successful PhD defenses. ### Source excerpt An expert in machine learning, statistics, and computation, Rakhlin succeeds Professor Ankur Moitra. ## Professor Emeritus Dimitri Bertsekas, influential computer scientist and prolific author, dies at 83 DevFeed: [Professor Emeritus Dimitri Bertsekas, influential computer scientist and prolific author, dies at 83]() Original publisher: [Read original article]() Author: Jane Halpern | Department of Electrical Engineering and Computer Science Published: 2026-07-22T17:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Optimization](), [Computer science](), [Electrical engineering and computer science (EECS)](), [AI Research](), [Artificial Intelligence](), [Reinforcement learning]() Tags: [alumni-ae](), [artificial-intelligence](), [asu-ozdaglar](), [athena-scientific](), [bayforest-technologies](), [books-and-authors](), [computer-science](), [computer-science-and-technology](), [convex-analysis](), [dimitri-bertsekas](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [laboratory-for-information-and-decision-systems-lids](), [large-scale-computation](), [mit-books-and-authors](), [mit-eecs-faculty](), [mit-faculty-obituary](), [mit-lids](), [mit-photographers](), [mit-sandbox-innovation-fund-program](), [mit-schwarzman-college-of-computing](), [munther-dahleh](), [network-optimization](), [networks](), [neurodynamic-programming](), [obituaries](), [optimization](), [photography](), [programming](), [reinforcement-learning](), [research](), [robert-gallager](), [school-of-engineering]() ### AI overview An obituary remembers Dimitri Bertsekas, an MIT professor emeritus and influential computer scientist who died at 83. His work shaped optimization, control, large-scale computation, reinforcement learning, and artificial intelligence, while his books and mentorship influenced generations of students and researchers. ### Source excerpt Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence. ## Bailey Flanigan uses computational and mathematical tools to study democratic participation DevFeed: [Bailey Flanigan uses computational and mathematical tools to study democratic participation]() Original publisher: [Read original article]() Author: Michaela Jarvis | MIT Laboratory for Information and Decision Systems Published: 2026-07-17T17:25:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Computer science](), [Electrical engineering and computer science (EECS)](), [Mathematics](), [MIT Schwarzman College of Computing]() Tags: [ai-and-democracy](), [ai-in-politics](), [algorithms](), [artificial-intelligence](), [bailey-flanigan](), [computer-science](), [computer-science-and-technology](), [defending-democracy](), [democracy](), [democratic-decision-making](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [government](), [labor-and-jobs](), [laboratory-for-information-and-decision-systems-lids](), [math](), [mit-eecs-faculty](), [mit-faculty-profile](), [mit-lids](), [mit-political-science](), [mit-schwarzman-college-of-computing](), [political-legitimacy](), [political-science](), [politics](), [profile](), [public-health](), [research](), [school-of-engineering](), [school-of-humanities-arts-and-social-sciences](), [science](), [technology-and-society](), [wisconsin-innocence-project]() ### AI overview An MIT faculty member, Bailey Flanigan studies how computational and mathematical tools can create new avenues for meaningful democratic participation. The article describes her interdisciplinary path across computer science, political science, medicine, public health, economics, and related fields. ### Source excerpt Assistant Professor Bailey Flanigan has arrived at complex computational methods for helping democracy thrive. ## Devavrat Shah's research and Ikigai Labs use tabular data for real-time forecasting and decision-making DevFeed: [Devavrat Shah's research and Ikigai Labs use tabular data for real-time forecasting and decision-making]() Original publisher: [Read original article]() Author: David Chandler | Laboratory for Information and Decision Systems Published: 2026-07-14T20:25:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [decision-making](), [Structured-data](), [AI Models](), [data](), [Time Series](), [Computer science](), [Electrical engineering and computer science (EECS)](), [Temporal data](), [systems]() Tags: [ai](), [ai-and-decision-making](), [ai-in-business-planning](), [ai-models](), [algorithms](), [artificial-intelligence](), [business-and-management](), [business-modeling](), [celonis-context-model](), [computer-science-and-technology](), [data](), [data-systems](), [decision-making](), [devavrat-shah](), [electrical-engineering-and-computer-science-eecs](), [faculty](), [forecasting](), [idss](), [ikigailabs](), [laboratory-for-information-and-decision-systems-lids](), [mit-eecs](), [mit-idss](), [mit-intellectual-property](), [mit-lids](), [mit-schwarzman-college-of-computing](), [predictions](), [profile](), [real-time](), [research](), [school-of-engineering](), [startups](), [structured](), [tabular-data](), [time-series-data]() ### AI overview MIT Professor Devavrat Shah's research led to a foundation model for tabular and time-series enterprise data. Developed with Ikigai Labs, the system continuously tests predictions against real outcomes to support large-scale forecasting and decision-making. ### Source excerpt Through research and entrepreneurship, Professor Devavrat Shah is helping to design methods that can handle constant decision-making using limited computational resources. ## New method aims to keep kids safe from illegal AI-generated content DevFeed: [New method aims to keep kids safe from illegal AI-generated content]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-07-13T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [ai safety](), [AI Research](), [Open Source]() Tags: [ai](), [ai-deepfakes](), [ai-safety](), [algorithms](), [artificial-intelligence](), [ashia-wilson](), [computer-science-and-technology](), [csam](), [ethics](), [generative](), [generative-ai](), [human-computer-interaction](), [institute-for-medical-engineering-and-science-imes](), [laboratory-for-information-and-decision-systems-lids](), [machine-learning](), [marzyeh-ghassemi](), [mit-schwarzman-college-of-computing](), [models](), [online-child-safety](), [open-source](), [privacy](), [public-health](), [research](), [safety](), [school-of-engineering](), [vinith-suriyakumar]() ### AI overview MIT researchers and Thorn developed an auditing technique that assesses whether a generative AI model has been specialized to produce child sexual abuse material without generating illegal outputs. In testing, the procedure identified specialized model variants with 100 percent accuracy. ### Source excerpt Researchers developed an auditing technique to test generative AI models for malicious capabilities, without prompting them for illegal outputs. ## New chip could help tiny robots traverse complex environments DevFeed: [New chip could help tiny robots traverse complex environments]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-06-23T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Hardware](), [Algorithms](), [3D](), [navigation](), [real-time](), [Green Software](), [Computer science]() Tags: [3d](), [aeronautical-and-astronautical-engineering](), [algorithms](), [artificial-intelligence](), [assembly](), [augmented-and-virtual-reality](), [autonomous-vehicles](), [computer-chips](), [computer-science-and-technology](), [efficiency](), [electrical-engineering-and-computer-science-eecs](), [energy](), [energy-efficiency](), [gleanmer](), [hardware](), [inside](), [laboratory-for-information-and-decision-systems-lids](), [low-power](), [machine-learning](), [memory](), [mit-schwarzman-college-of-computing](), [national-science-foundation-nsf](), [navigation](), [peter-zhi-xuan-li](), [real-time](), [research](), [research-laboratory-of-electronics](), [robotics](), [school-of-engineering](), [sertac-karaman](), [system-on-a-chip](), [trajectory-planning](), [vivienne-sze](), [zih-sing-fu]() ### AI overview MIT researchers developed a low-power chip that combines an efficient mapping algorithm with dedicated hardware to generate detailed 3D maps for robot navigation in real time. The system-on-a-chip uses about 6 milliwatts and is intended for tiny autonomous robots and other battery-limited devices. ### Source excerpt Researchers combined an efficient algorithm with dedicated hardware to rapidly generate 3D maps for navigation using minimal memory and power. ## MIT researchers develop a real-time spatiotemporal memory framework for robots DevFeed: [MIT researchers develop a real-time spatiotemporal memory framework for robots]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-06-17T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Robotics](), [Artificial Intelligence](), [Computer vision]() Tags: [3d-scene-graphs](), [aeronautical-and-astronautical-engineering](), [ai](), [algorithms](), [artificial-intelligence](), [autonomous-vehicles](), [computer-science-and-technology](), [computer-vision](), [daaam](), [describe-anything-anywhere-at-any-moment](), [electrical-engineering-and-computer-science-eecs](), [laboratory-for-information-and-decision-systems-lids](), [luca-carlone](), [machine-learning](), [map](), [memory](), [mit-schwarzman-college-of-computing](), [nicolas-gorlo](), [paper](), [real-time](), [research](), [robot-memory](), [robotic-perception](), [robotics](), [robots](), [school-of-engineering](), [spatial](), [spatiotemporal-mapping]() ### AI overview MIT researchers developed a long-term spatiotemporal memory framework that helps robots form and recall detailed models of large environments. The system combines map representations with language-based descriptions, answers environmental questions in plain language, and runs fast enough for real-time mobile-robot use. ### Source excerpt A new spatial memory system for robots efficiently captures details about the objects they see while exploring their environment.