# Horizon-Coupled Obstacle Guidance: inference-time obstacle avoidance guidance for relative-action diffusion policies

- Source: arXiv cs.RO
- Published: 2026-11-09T05:00:00.000Z
- RoboHot: https://robohot.news/en/items/bckc1hq0ohsgs045towp39m9l
- Original: https://arxiv.org/abs/2611.09340

## Summary

This research proposes an inference-time 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 during denoising propagates each obstacle response to all contributing action increments. In real-robot experiments across seven obstacle-constrained scenarios spanning four manipulation tasks, the method achieved 105/140 (75.0%) collision-free task successes, compared with 8/140 (5.7%) for absolute-action pointwise guidance. Ablations show that the temporally coupled form of relative actions yields larger gains under both obstacle models.