REx Lab: Home
The Robotic Exploration Lab in The Department of Aeronautics and Astronautics at MIT conducts research in control, motion planning, and navigation for robotic systems that explore our planet and our universe. Test-time planning steers whole-body robot policies to manipulate large and heavy objects in the real world. An algorithm to design globally optimal low-thrust collision-avoidance maneuvers for short-term conjunction events. A single whole-body linearization is sufficient for basic locomotion tasks on humanoids and quadrupeds. Unifying Sequential-Convex Programming and Sampling-Based Trajectory Optimization for robust motion planning. The first successful deployment of a whole-body sampling-based MPC system on a real-world quadruped robot. A convex model predictive control approach for stationkeeping maneuver design of unstable halo orbits. Real-time whole-body model-predictive control of quadruped and humanoid robotics using the MuJoCo physics engine. Data-driven, linear output-f
The Robotic Exploration Lab in The Department of Aeronautics and Astronautics at MIT conducts research in control, motion planning, and navigation for robotic systems that explore our planet and our universe. Research Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation Test-time planning steers whole-body robot policies to manipulate large and heavy objects in the real world. Read more » Convex Maneuver Planning for Spacecraft Collision Avoidance An algorithm to design globally optimal low-thrust collision-avoidance maneuvers for short-term conjunction events. Read more »…
saved by
related reading
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io
- [2509.05397] RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learningarxiv.org
- Ch. 7 - Mobile Manipulationmanipulation.csail.mit.edu
- Versatile Loco-Manipulation through Flexible Interlimb Coordinationarxiv.org
- Robust Regression for Safe Exploration in Controlarxiv.org
- Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learningarxiv.org
- UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robotsarxiv.org
- Deep Whole-Body Control: End-to-End Learning in Legged Manipulator Robotsyoutube.com
- Generating Robot Hands from Human Demonstrationsarxiv.org
- Ch. 2 - Let's get you a robotmanipulation.csail.mit.edu
- biomimetics.mit.edubiomimetics.mit.edu