Risk‐Aware Motorcycle Interaction in Mixed Traffic Flow via Deep Reinforcement Learning

ABSTRACT This paper introduces a reinforcement learning framework for simulating ego‐motorcycle behavior in mixed traffic for animation‐oriented applications. A local path planner uses ray‐based perception to guide navigation, while a tailored reward structure promotes safe interactions and penalizes hazardous maneuvers. To support action selection, the planner also constructs a risk‐probability map that captures nearby vehicles' speeds and distances. Curriculum learning gradually increases traffic complexity during training, enabling the policy to adapt to a wide range of scenarios. Experimental results show that the trained policy produces collision‐free trajectories, responsive deceleration, and well‐regulated maneuvering. It also occasionally exhibits assertive or borderline‐risky interactions that enhance behavioral naturalness. These findings demonstrate that the framework can generate structured yet varied motorcycle motion. Potential applications include entertainment media, educational visualizations, and driver‐training simulations, enriching animated content for learning and engagement.