How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?
Diffusion policies have shown impressive results in robot imitation learning, even for tasks that require satisfaction of kinematic equality constraints. However, task performance alone is not a reliable indicator of the policy's ability to precisely learn constraints in the training data. To investigate, we analyze how well diffusion policies discover these manifolds with a case study on a bimanual pick-and-place task that encourages fulfillment of a kinematic constraint for success. We study how three factors affect trained policies: dataset size, dataset quality, and manifold curvature. Our experiments show diffusion policies learn a coarse approximation of the constraint manifold with learning affected negatively by decreases in both dataset size and quality. On the other hand, the curvature of the constraint manifold showed inconclusive correlations with both constraint satisfaction and task success. A hardware evaluation verifies the applicability of our results in the real world. Project website with additional results and visuals: https://diffusion-learns-kinematic.github.io
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their stren…
Motion SynthesisHierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
This paper introduces Hierarchical Diffusion Policy (HDP), a hierarchical agent for multi-task robotic manipulation. HDP factorises a manipulation policy into a hierarchical structure: a high-level task-planning agent wh…
PositionTask PlanningThe Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term the $\textbf{Euclidean Fallacy}$: representing SE(3) poses as flat $\ma…
PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation
Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predictive Control (MPC) explicitly handle rob…
Robot NavigationLearning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance
Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does no…
Imitation Learning