Robot Locomotion Group
Videos from the Robot Locomotion Group at the MIT Computer Science and Artificial Intelligence Laboratory.
The goal of our research is to build machines which exploit their natural dynamics to achieve extraordinary agility and efficiency. We believe that this challenge involves a tight coupling between mechanical design and underactuated nonlinear control, and that tools from machine learning and optimal control can be used to produce this coupling when classical control techniques fail. Our projects include minimally-actuated dynamic walking on moderate terrain, quadrupedal locomotion on extreme terrain, fixed-wing acrobatics, flapping-winged flight, and feedback control for fluid dynamics.
The Robot Locomotion Group is a part of the CSAIL Center for Robotics.
Leveraging Structure for Efficient and Dexterous Contact-Rich Manipulation
Graphs of Convex Sets with applications to optimal control and motion planning
Motion Planning around Obstacles with Convex Optimization
Fast Path Planning Through Large Collections of Safe Boxes
Tao Pang's Ph.D. Thesis Defense (Jan 20, 2023)
Scalable Verification of Robots and Recurrent Networks -- Shen Shen's Thesis Defense
Self-Supervised Correspondence in Visuomotor Policy Learning
Dense Visual Learning for Robot Manipulation
A Supervised Approach to Predicting Noise in Depth Images
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation (extended technical version)
SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction
Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
NanoMap: Fast, Uncertainty-Aware Proximity Queries with Lazy Search over Local 3D Data
Global Inverse Kinematics via Mixed-Integer Convex Optimization
Team MIT at the 2015 DARPA Robotics Challenge Finals
Planning robust walking motion on uneven terrain via convex optimization
Tracking Objects with Point Clouds from Vision and Touch
Funnel Libraries for Real-Time Robust Feedback Motion Planning (Anirudha Majumdar)
Small Drone Dodging Obstacles at High Speed using Funnel Libraries
High-Speed Autonomous Obstacle Avoidance with Pushbroom Stereo (Andy Barry)
Pushbroom Stereo for High-Speed Obstacle Avoidance (technical video)
Planning and Control for Quadrotor Flight through Cluttered Environments
Feedback-motion-planning with simulation-based LQR-trees
Exploiting the complementarity structure: stability analysis of contact dynamics via sums-of-squares
Efficient Mixed-Integer Trajectory Planning for UAVs
Pushbroom stereo for high-speed navigation in cluttered environments