Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigation

The paper introduces Planning Diffusion Policy Optimization (PDPO), an offline‑to‑online reinforcement‑learning framework that employs a diffusion policy to produce short‑horizon action chunks for robot crowd navigation. PDPO is pretrained on collision‑avoidance demonstrations and fine‑tuned online with PPO, generating five‑step action sequences applied in a receding‑horizon manner. The authors also identify a benchmark artifact where agents can leave the valid domain without explicit boundary constraints, and they mitigate this by treating boundary violations as collisions, leading to improved success rates over strong baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• agents
• diffusion
• reinforcement-learning
• robotics
• fine-tuning
• multimodal
• benchmarks