Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation

TL;DR

This paper introduces a kinematics-aware diffusion policy framework for whole-arm robotic manipulation, aligning observation and action spaces in 3D to improve learning efficiency and generalization in complex manipulation tasks.

Contribution

It proposes a novel 3D space-aligned imitation learning framework with diffusion policies and kinematic priors, enhancing policy feasibility and spatial generalization for whole-arm control.

Findings

Higher success rates in simulation and real-world tests

Improved sample efficiency and spatial generalizability

Effective integration of kinematic priors into diffusion policies

Abstract

Whole-body control of robotic manipulators with awareness of full-arm kinematics is crucial for many manipulation scenarios involving body collision avoidance or body-object interactions, which makes it insufficient to consider only the end-effector poses in policy learning. The typical approach for whole-arm manipulation is to learn actions in the robot's joint space. However, the unalignment between the joint space and actual task space (i.e., 3D space) increases the complexity of policy learning, as generalization in task space requires the policy to intrinsically understand the non-linear arm kinematics, which is difficult to learn from limited demonstrations. To address this issue, this letter proposes a kinematics-aware imitation learning framework with consistent task, observation, and action spaces, all represented in the same 3D space. Specifically, we represent both robot states and actions using a set of 3D points on the arm body, naturally aligned with the 3D point cloud observations. This spatially consistent representation improves the policy's sample efficiency and spatial generalizability while enabling full-body control. Built upon the diffusion policy, we further incorporate kinematics priors into the diffusion processes to guarantee the kinematic feasibility of output actions. The joint angle commands are finally calculated through an optimization-based whole-body inverse kinematics solver for execution. Simulation and real-world experimental results demonstrate higher success rates and stronger spatial generalizability of our approach compared to existing methods in body-aware manipulation policy learning.