# self-driving cars

Published articles for self-driving cars.

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

## System helps humans predict when self-driving cars will make mistakes

DevFeed: [System helps humans predict when self-driving cars will make mistakes](<https://devfeed.tech/articles/system-helps-humans-predict-when-self-driving-cars-will-make-mistakes-37982.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/system-helps-humans-predict-when-self-driving-cars-will-make-mistakes-0902>)

Author: Adam Zewe | MIT News

Published: 2026-09-02T15:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [Computer science](<https://devfeed.tech/topics/computer-science.md>)

Tags: [aeronautical-and-astronautical-engineering](<https://devfeed.tech/tags/aeronautical-and-astronautical-engineering.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [computer-science-and-artificial-intelligence-laboratory-csail](<https://devfeed.tech/tags/computer-science-and-artificial-intelligence-laboratory-csail.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [concept-wrapper-network](<https://devfeed.tech/tags/concept-wrapper-network.md>), [cw-net](<https://devfeed.tech/tags/cw-net.md>), [deep](<https://devfeed.tech/tags/deep.md>), [electrical-engineering-and-computer-science-eecs](<https://devfeed.tech/tags/electrical-engineering-and-computer-science-eecs.md>), [eoin-kenny](<https://devfeed.tech/tags/eoin-kenny.md>), [human-computer-interaction](<https://devfeed.tech/tags/human-computer-interaction.md>), [julie-shah](<https://devfeed.tech/tags/julie-shah.md>), [laura-major](<https://devfeed.tech/tags/laura-major.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [momchil-tomov](<https://devfeed.tech/tags/momchil-tomov.md>), [motional](<https://devfeed.tech/tags/motional.md>), [research](<https://devfeed.tech/tags/research.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [safety](<https://devfeed.tech/tags/safety.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [self-driving](<https://devfeed.tech/tags/self-driving.md>), [self-driving-cars](<https://devfeed.tech/tags/self-driving-cars.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [transparency](<https://devfeed.tech/tags/transparency.md>)

### AI overview

MIT and Motional researchers developed CW-Net, a method that translates an autonomous vehicle's deep-learning decisions into understandable concepts. Tests found that the explanations helped safety drivers and nonexpert users better predict vehicle behavior.

### Source excerpt

A new method, called CW-Net, translates the reasoning process of an autonomous vehicle's AI system into understandable concepts that explain its behavior.