Autonomous Vehicle Research in Mixed-Traffic Environments

The field of autonomous vehicle research is moving towards developing more sophisticated models that can effectively interact with human-driven vehicles in mixed-traffic environments. Recent studies have focused on improving the decision-making capabilities of autonomous vehicles, taking into account the diverse behaviors and driving styles of human drivers. The use of reinforcement learning, graph neural networks, and intention-driven frameworks has shown promising results in enhancing the safety, efficiency, and stability of autonomous vehicle navigation. Noteworthy papers include:

  • One that proposed a heterogeneous graph reinforcement learning approach, which achieved superior performance in a case study on a four-way intersection.
  • Another that developed an intention-driven lane change framework, which outperformed rule-based and learning-based baselines by 4-15% in lane change recognition.

Sources

Impact of Collective Behaviors of Autonomous Vehicles on Urban Traffic Dynamics: A Multi-Agent Reinforcement Learning Approach

An Intention-driven Lane Change Framework Considering Heterogeneous Dynamic Cooperation in Mixed-traffic Environment

Cooperative Autonomous Driving in Diverse Behavioral Traffic: A Heterogeneous Graph Reinforcement Learning Approach

Preemptive Spatiotemporal Trajectory Adjustment for Heterogeneous Vehicles in Highway Merging Zones

Built with on top of