Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic
A dual-driven learning framework enhances autonomous vehicle decision-making in complex, human-centric traffic scenarios.
In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into reinforcement learning (RL) models fail to capture latent interactive vehicle intentions and diverse driver behaviors, limiting t...
ArXiv CS.RO
Source
Generated insight by OnAirToday AI
This research bridges the gap between raw data processing and physical reasoning by integrating predictive behavioral modeling into reinforcement learning frameworks. By enabling autonomous vehicles to proactively interpret human intent, this dual-driven approach significantly improves safety and decision-making fluidity in unpredictable traffic environments.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.