Hierarchical Learning-Enhanced MPC for Safe Crowd Navigation with Heterogeneous Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912497745788928 |
|---|---|
| author | Liu, Huajian Feng, Yixuan Dong, Wei Fan, Kunpeng Wang, Chao Gao, Yongzhuo |
| author_facet | Liu, Huajian Feng, Yixuan Dong, Wei Fan, Kunpeng Wang, Chao Gao, Yongzhuo |
| contents | In this paper, we propose a novel hierarchical framework for robot navigation in dynamic environments with heterogeneous constraints. Our approach leverages a graph neural network trained via reinforcement learning (RL) to efficiently estimate the robot's cost-to-go, formulated as local goal recommendations. A spatio-temporal path-searching module, which accounts for kinematic constraints, is then employed to generate a reference trajectory to facilitate solving the non-convex optimization problem used for explicit constraint enforcement. More importantly, we introduce an incremental action-masking mechanism and a privileged learning strategy, enabling end-to-end training of the proposed planner. Both simulation and real-world experiments demonstrate that the proposed method effectively addresses local planning in complex dynamic environments, achieving state-of-the-art (SOTA) performance. Compared with existing learning-optimization hybrid methods, our approach eliminates the dependency on high-fidelity simulation environments, offering significant advantages in computational efficiency and training scalability. The code will be released as open-source upon acceptance of the paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09859 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Learning-Enhanced MPC for Safe Crowd Navigation with Heterogeneous Constraints Liu, Huajian Feng, Yixuan Dong, Wei Fan, Kunpeng Wang, Chao Gao, Yongzhuo Robotics In this paper, we propose a novel hierarchical framework for robot navigation in dynamic environments with heterogeneous constraints. Our approach leverages a graph neural network trained via reinforcement learning (RL) to efficiently estimate the robot's cost-to-go, formulated as local goal recommendations. A spatio-temporal path-searching module, which accounts for kinematic constraints, is then employed to generate a reference trajectory to facilitate solving the non-convex optimization problem used for explicit constraint enforcement. More importantly, we introduce an incremental action-masking mechanism and a privileged learning strategy, enabling end-to-end training of the proposed planner. Both simulation and real-world experiments demonstrate that the proposed method effectively addresses local planning in complex dynamic environments, achieving state-of-the-art (SOTA) performance. Compared with existing learning-optimization hybrid methods, our approach eliminates the dependency on high-fidelity simulation environments, offering significant advantages in computational efficiency and training scalability. The code will be released as open-source upon acceptance of the paper. |
| title | Hierarchical Learning-Enhanced MPC for Safe Crowd Navigation with Heterogeneous Constraints |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.09859 |