Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909385924542464 |
|---|---|
| author | Vijayakumar, Akash A, Atmanand M Somayajula, Abhilash |
| author_facet | Vijayakumar, Akash A, Atmanand M Somayajula, Abhilash |
| contents | This paper presents an approach for autonomous docking of a fully actuated autonomous surface vessel using expert demonstration data. We frame the docking problem as an imitation learning task and employ inverse reinforcement learning (IRL) to learn a reward function from expert trajectories. A two-stage neural network architecture is implemented to incorporate both environmental context from sensors and vehicle kinematics into the reward function. The learned reward is then used with a motion planner to generate docking trajectories. Experiments in simulation demonstrate the effectiveness of this approach in producing human-like docking behaviors across different environmental configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07550 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data Vijayakumar, Akash A, Atmanand M Somayajula, Abhilash Robotics This paper presents an approach for autonomous docking of a fully actuated autonomous surface vessel using expert demonstration data. We frame the docking problem as an imitation learning task and employ inverse reinforcement learning (IRL) to learn a reward function from expert trajectories. A two-stage neural network architecture is implemented to incorporate both environmental context from sensors and vehicle kinematics into the reward function. The learned reward is then used with a motion planner to generate docking trajectories. Experiments in simulation demonstrate the effectiveness of this approach in producing human-like docking behaviors across different environmental configurations. |
| title | Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data |
| topic | Robotics |
| url | https://arxiv.org/abs/2411.07550 |