For safe operation, autonomous vehicles have to obey traffic rules that are set forth in legal documents formulated in natural language. Temporal logic is a suitable concept to formalize such traffic rules. Still, temporal logic rules often result in constraints that are hard to solve using optimization-based motion planners. Reinforcement learning (RL) is a promising method to find motion plans for autonomous vehicles. However, vanilla RL algorithms are based on random exploration and do not automatically comply with traffic rules. Our approach accomplishes guaranteed rule-compliance by integrating temporal logic specifications into RL. Specifically, we consider the application of vessels on the open sea, which must adhere to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). To efficiently synthesize rule-compliant actions, we combine predicates based on set-based prediction with a statechart representing our formalized rules and their priorities. Action masking then restricts the RL agent to this set of verified rule-compliant actions. In numerical evaluations on critical maritime traffic situations, our agent always complies with the formalized legal rules and never collides while achieving a high goal-reaching rate during training and deployment. In contrast, vanilla and traffic rule-informed RL agents frequently violate traffic rules and collide even after training.


    Access

    Download


    Export, share and cite



    Title :

    Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea


    Contributors:

    Published in:

    Publication date :

    2024-12-01


    Size :

    3172360 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Safe and Rule-Aware Deep Reinforcement Learning for Autonomous Driving at Intersections

    Zhang, Chi / Kacem, Kais / Hinz, Gereon et al. | IEEE | 2022


    Towards Data Driven Traffic Modelling: Safe Driving Based on Reinforcement Learning*

    Kyriazopoulos, Vasilis / Orfanou, Foteini / Vlahogianni, Eleni I. et al. | IEEE | 2021


    A Reinforcement Learning Approach to Quiet and Safe UAM Traffic Management

    Murthy, Surya / Clarke, John-Paul / Topcu, Ufuk et al. | ArXiv | 2025

    Free access

    A Reinforcement Learning Approach to Quiet and Safe UAM Traffic Management

    Murthy, Surya K. / Gao, Zhenyu / Clarke, John-Paul B. et al. | AIAA | 2025