Helping robots zero in on the objects that matter
A new method called Clio enables robots to quickly map a scene and identify the items they need to complete a given set of tasks.
A new method called Clio enables robots to quickly map a scene and identify the items they need to complete a given set of tasks.
Neural network controllers provide complex robots with stability guarantees, paving the way for the safer deployment of autonomous vehicles and industrial machines.
This technique could lead to safer autonomous vehicles, more efficient AR/VR headsets, or faster warehouse robots.
By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.
Autonomous helicopters made by Rotor Technologies, a startup led by MIT PhDs, take the human out of risky commercial missions.
The system could improve image quality in video streaming or help autonomous vehicles identify road hazards in real-time.
Jonathan How and his team at the Aerospace Controls Laboratory develop planning algorithms that allow autonomous vehicles to navigate dynamic environments without colliding.
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
Luca Carlone and Jonathan How of MIT LIDS discuss how future robots might perceive and interact with their environment.
A new AI-based approach for controlling autonomous robots satisfies the often-conflicting goals of safety and stability.