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.
By Wendong Li, Jochen Garcke
arXiv:2606. 14763v1 Announce Type: cross Abstract: Real-time autonomous navigation in dynamic, unknown environments remains a fundamental challenge for mobile robotics.
By Lorenzo Ortolani, Gabriel Voss, Gabriele Beltrami, Francesco Dorati, Tommaso Felice Banfi
arXiv:2609.13083v2 Announce Type: replace-cross
Abstract: In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and c...
By Zhenfeng Gan, Yanbo Chen, Lirong Che, Junbo Tan, Xueqian Wang
The paper introduces ASTRIL-MPC, a language‑guided neural model predictive control framework that enables articulated tracked robots to navigate complex, contact‑rich urban environments such as stairwells and cluttered interiors. By combining a learned kinematics model that predicts short‑horizon state changes, an optimization‑based planner with multi‑objective costs, and a large language model that safely updates control weights, the system achieves up to 71% better traversal quality than non‑adaptive NMPC and 67% better than a PPO baseline, while eliminating collision impacts during descent. Real‑robot trials over four indoor obstacles confirm the method’s transferability to physical contact‑rich traversal.
By Zhenfeng Gan, Yanbo Chen, Lirong Che, Yongyi Ma, Rongkai Zhu, Xueqian Wang
arXiv:2608. 09166v1 Announce Type: cross Abstract: Reliable uncertainty representation is essential for deploying autonomous systems that interact with their environment, as robots must reason about how uncertainty arising from both stochasticity and model mismatch is impacted by contacts with obstacles (e.
By Lu\'is Marques, Kristian Popov, Dmitry Berenson
arXiv:2604.15221v3 Announce Type: replace-cross
Abstract: Safe human-robot collaboration (HRC) requires accurate human pose estimation and motion prediction to prevent critical collisions. Existing c...
By Jakob Thumm, Marian Frei, Tianle Ni, Matthias Althoff, Marco Pavone