Falsification-Driven Reinforcement Learning for Maritime Motion Planning
This work addresses safety-critical motion planning for autonomous vessels, representing an incremental improvement in domain-specific RL training.
The paper tackles the challenge of training reinforcement learning agents to comply with maritime traffic rules by proposing a falsification-driven approach that generates adversarial training scenarios, resulting in more consistent rule compliance in open-sea navigation experiments.
Compliance with maritime traffic rules is essential for the safe operation of autonomous vessels, yet training reinforcement learning (RL) agents to adhere to them is challenging. The behavior of RL agents is shaped by the training scenarios they encounter, but creating scenarios that capture the complexity of maritime navigation is non-trivial, and real-world data alone is insufficient. To address this, we propose a falsification-driven RL approach that generates adversarial training scenarios in which the vessel under test violates maritime traffic rules, which are expressed as signal temporal logic specifications. Our experiments on open-sea navigation with two vessels demonstrate that the proposed approach provides more relevant training scenarios and achieves more consistent rule compliance.