Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data

TL;DR

This paper frames the docking problem as an imitation learning task and employs inverse reinforcement learning (IRL) to learn a reward function from expert trajectories to incorporate both environmental context from sensors and vehicle kinematics into the reward function.

Abstract

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.

Figures (8)

• Figure 1: Simulation Environment
• Figure 2: Input Feature Maps
• Figure 3: Input Kinematics Feature Maps
• Figure 4: Input Environmental Map and Reward Map from Network
• Figure 5: Network Architecture