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, developed by MIT CSAIL researchers, combines 3D scene reconstruction with embodied representation and closed-loop control.
Robot, know thyself: New vision-based system teaches machines to understand their bodies Neural Jacobian Fields, developed by MIT CSAIL researchers, can learn to control any robot from a single camera, without any other sensors.
MIT researchers developed a powerful system that could help robots safely navigate unpredictable environments using only images captured from their onboard cameras.
The word “robot” was coined by the Czech writer Karel Čapek in a 1920 play called Rossum’s Universal Robots, and is derived from the Czech robota, meaning “drudgery” or “servitude”.
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.
MIT Associate Professor Luca Carlone works to give robots a more human-like perception of their environment, so they can interact with people safely and seamlessly.
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 CSAIL algorithm enables autonomous practice to improve at mobile-manipulation activities.
Robots are helping humans in a growing number of places – from archaeological sites to disaster zones and sewers. The most recent robotic inventions can entertain people in care homes and squeeze into small spaces. Robotics engineers are among the top 20 job types on a growth trajectory, according to the World Economic Forum's Future of Jobs Report 2025.
A hopping, insect-sized robot can jump over gaps or obstacles, traverse rough, slippery, or slanted surfaces, and perform aerial acrobatic maneuvers, while using a fraction of the energy required for flying microbots.
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 used in smart manufacturing and warehouse settings where robots would work alongside and assist humans.
