Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2602.05608 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912936634613760 |
|---|---|
| author | Zhu, Yufei Yang, Shih-Min Magnusson, Martin Wang, Allan |
| author_facet | Zhu, Yufei Yang, Shih-Min Magnusson, Martin Wang, Allan |
| contents | Navigating through dense human crowds remains a significant challenge for mobile robots. A key issue is the freezing robot problem, where the robot struggles to find safe motions and becomes stuck within the crowd. To address this, we propose HiCrowd, a hierarchical framework that integrates reinforcement learning (RL) with model predictive control (MPC). HiCrowd leverages surrounding pedestrian motion as guidance, enabling the robot to align with compatible crowd flows. A high-level RL policy generates a follow point to align the robot with a suitable pedestrian group, while a low-level MPC safely tracks this guidance with short horizon planning. The method combines long-term crowd aware decision making with safe short-term execution. We evaluate HiCrowd against reactive and learning-based baselines in offline setting (replaying recorded human trajectories) and online setting (human trajectories are updated to react to the robot in simulation). Experiments on a real-world dataset and a synthetic crowd dataset show that our method outperforms in navigation efficiency and safety, while reducing freezing behaviors. Our results suggest that leveraging human motion as guidance, rather than treating humans solely as dynamic obstacles, provides a powerful principle for safe and efficient robot navigation in crowds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05608 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HiCrowd: Hierarchical Crowd Flow Alignment for Dense Human Environments Zhu, Yufei Yang, Shih-Min Magnusson, Martin Wang, Allan Robotics Navigating through dense human crowds remains a significant challenge for mobile robots. A key issue is the freezing robot problem, where the robot struggles to find safe motions and becomes stuck within the crowd. To address this, we propose HiCrowd, a hierarchical framework that integrates reinforcement learning (RL) with model predictive control (MPC). HiCrowd leverages surrounding pedestrian motion as guidance, enabling the robot to align with compatible crowd flows. A high-level RL policy generates a follow point to align the robot with a suitable pedestrian group, while a low-level MPC safely tracks this guidance with short horizon planning. The method combines long-term crowd aware decision making with safe short-term execution. We evaluate HiCrowd against reactive and learning-based baselines in offline setting (replaying recorded human trajectories) and online setting (human trajectories are updated to react to the robot in simulation). Experiments on a real-world dataset and a synthetic crowd dataset show that our method outperforms in navigation efficiency and safety, while reducing freezing behaviors. Our results suggest that leveraging human motion as guidance, rather than treating humans solely as dynamic obstacles, provides a powerful principle for safe and efficient robot navigation in crowds. |
| title | HiCrowd: Hierarchical Crowd Flow Alignment for Dense Human Environments |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.05608 |