7 papers
Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics
Adam Wei, Nicholas Pfaff, Thomas Cohn +4
We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and…
SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
Nicholas Pfaff, Thomas Cohn, Sergey Zakharov +2
Simulation has become a key tool for training and evaluating home robots at scale, yet existing environments fail to capture the diversity and physical complexity of real indoor sp…
A Framework for Combining Optimization-Based and Analytic Inverse Kinematics
Thomas Cohn, Lihan Tang, Alexandre Amice +1
Analytic and optimization methods for solving inverse kinematics (IK) problems have been deeply studied throughout the history of robotics. The two strategies have complementary st…
How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?
Lexi Foland, Thomas Cohn, Adam Wei +3
Diffusion policies have shown impressive results in robot imitation learning, even for tasks that require satisfaction of kinematic equality constraints. However, task performance…
Sampling-Based Motion Planning with Discrete Configuration-Space Symmetries
Thomas Cohn, Russ Tedrake
When planning motions in a configuration space that has underlying symmetries (e.g. when manipulating one or multiple symmetric objects), the ideal planning algorithm should take a…
Planning Shorter Paths in Graphs of Convex Sets by Undistorting Parametrized Configuration Spaces
Shruti Garg, Thomas Cohn, Russ Tedrake
Optimization based motion planning provides a useful modeling framework through various costs and constraints. Using Graph of Convex Sets (GCS) for trajectory optimization gives gu…