cs.RONov 6, 2026

Horizon-Coupled Obstacle Guidance for Relative-Action Diffusion Policies

Authors: Guangyuan Wang, Haishan Xia, Zitao Zhang, Kejia Chen, Yuanchen Sun, Zhenguo Sun, Donghao Zhang, Yu Zhang, 

Organizations: School of Computation, Information and Technology, Technical University of Munich, Germany. · Beijing Information Science and Technology University, China.

Abstract

Real-world robot deployment requires adapting learned policies to unseen obstacles without collecting new demonstrations or retraining. Existing policy-level guidance often applies obstacle corrections independently at individual horizon steps, which may address local obstacle violations but fail to coordinate the action sequence into a complete, task-directed detour. How obstacle responses should be propagated across the action horizon to coordinate complete, task-directed avoidance motion remains underexplored. We introduce an inferencetime obstacle-guidance framework for pretrained relative-action diffusion policies. It rolls out cumulative relative actions into a workspace trajectory, evaluates obstacle interactions along the trajectory with an SDF-based obstacle model, and propagates each obstacle response to all contributing action increments during denoising. Real-robot experiments across seven obstacleconstrained scenarios spanning four manipulation tasks show that our method achieves 105/140 (75.0%) collision-free task successes, compared with 8/140 (5.7%) for absolute-action pointwise guidance. Ablations show that the relative-action horizoncoupled formulation provides the larger observed improvement across both obstacle models.

Figures & tables

Explore similar work

CardsList
  1. ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

    Sep 10, 2026Jiawen Wang, Kevin Yao, Khalid JawedDiffusion-Based PlanningGeneralization in Robotic Manipulation

  2. Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies

    Sep 28, 2026Weihang Guo, Lydia E. KavrakiCollision AvoidanceRobot Collision Avoidance

  3. DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles

    Sep 30, 2026Sanghyuk Park, Kwanwoo Lee, Taekyung Kim +2RL for RoboticsControl Barrier Functions