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.
Autonomous vehicles
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 the safer deployment of autonomous vehicles and industrial machines.
Researchers leverage shadows to model 3D scenes, including objects blocked from view
This technique could lead to safer autonomous vehicles, more efficient AR/VR headsets, or faster warehouse robots.
Researchers enhance peripheral vision in AI models
By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.
Safer skies with self-flying helicopters
Autonomous helicopters made by Rotor Technologies, a startup led by MIT PhDs, take the human out of risky commercial missions.
AI model speeds up high-resolution computer vision
The system could improve image quality in video streaming or help autonomous vehicles identify road hazards in real-time.
Autonomous innovations in an uncertain world
Jonathan How and his team at the Aerospace Controls Laboratory develop planning algorithms that allow autonomous vehicles to navigate dynamic environments without colliding.
A simpler method for learning to control a robot
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
3 Questions: Honing robot perception and mapping
Luca Carlone and Jonathan How of MIT LIDS discuss how future robots might perceive and interact with their environment.
A step toward safe and reliable autopilots for flying
A new AI-based approach for controlling autonomous robots satisfies the often-conflicting goals of safety and stability.