LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot Manipulation

2026-09-14

AI Summary

为解决机器人操作中轨迹不连续和不平滑问题，提出LieSpline-DP方法，通过Lie群B样条生成连续的末端执行器轨迹。

Abstract

Diffusion Policy (DP) is a powerful Learning from Demonstration (LfD) method for robotic manipulation, yet it suffers from discontinuous and non-smooth trajectories. Spline-based action representations promote smooth motion within individual action chunks, but existing spline-based methods neither guarantee cross-chunk $C^2$ continuity nor account for the group structure of $\mathrm{SE}(3)$. We therefore propose LieSpline-DP, a Lie-group B-spline diffusion policy that generates end-effector trajectories directly on $\mathrm{SE}(3)$ and couples consecutive plans by sharing their boundary control poses, ensuring $C^2$ continuity throughout the entire planned trajectory. Across three real-robot tasks, LieSpline-DP produces lower trajectory jerk and higher task success rates than the DP baseline. The gains are particularly pronounced in real-world tasks involving liquids and flexible objects: in our real-robot experiments, LieSpline-DP achieved a 100% success rate on both pouring and bucket hooking, whereas the DP baseline achieved only 10% and 30%, respectively.

Problem

• Diffusion Policy
• Learning from Demonstration
• Spline-based action representations
• C^2 continuity
• SE(3)

Innovation

• LieSpline-DP
• C^2 continuity
• SE(3)
• spline-based action representations
• robotic manipulation