Jun 5, 2025 · A new system enables a robot to “think ahead” and consider thousands of potential motion plans simultaneously, allowing the robot to solve a multistep problem in a few seconds.

Jul 24, 2025 · A vision-based control system called Neural Jacobian Fields enables soft and rigid robots to learn self-supervised motion control using only a monocular camera. The system, …

Mar 16, 2017 · A technique developed by MIT researchers uses Wi-Fi transmitters’ distinctive radio “fingerprints” to thwart spoofing attacks on multirobot systems. The method could provide …

Jan 31, 2025 · MIT engineers developed a training method for multiagent systems, such as large numbers of drones, that can guarantee their safe operation in crowded environments.

May 8, 2025 · MIT engineers developed a ping-pong-playing robot that quickly estimates the speed and trajectory of an incoming ball and precisely hits it to a desired location on the table.

Oct 8, 2025 · Robot, know thyself: New vision-based system teaches machines to understand their bodies Neural Jacobian Fields, developed by MIT CSAIL researchers, can learn to …

Jul 17, 2024 · Creating and verifying stable AI-controlled systems in a rigorous and flexible way Neural network controllers provide complex robots with stability guarantees, paving the way for …

Apr 24, 2025 · MIT roboticists developed a way to cut through data noise and help robots focus on the features in a scene that are most relevant for assisting humans. The system could be …

Jan 8, 2024 · A multimodal system uses models trained on language, vision, and action data to help robots develop and execute plans for household, construction, and manufacturing tasks.

Aug 8, 2024 · A robot rapidly specializes its skills using parameter policy learning, where the machine can rapidly specialize at specific, smaller actions within a long-horizon task. The MIT …