Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey
Autonomous driving (AD) holds the potential to revolutionize transportation efficiency, but its
success hinges on robust behavior planning (BP) mechanisms. Reinforcement learning (RL) …
success hinges on robust behavior planning (BP) mechanisms. Reinforcement learning (RL) …
Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis
X Wang, M Althoff - IEEE Transactions on Intelligent Vehicles, 2023 - ieeexplore.ieee.org
Ensuring safe and capable motion planning is paramount for automated vehicles.
Traditional methods are limited in their ability to handle complex and unpredictable traffic …
Traditional methods are limited in their ability to handle complex and unpredictable traffic …
Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors
The development of autonomous vehicles has shown great potential to enhance the
efficiency and safety of transportation systems. However, the decision-making issue in …
efficiency and safety of transportation systems. However, the decision-making issue in …
Safe reinforcement learning for lane-changing with comprehensive analysis of safety detection
S Li, S Yang, L Wang, Y Huang - 2023 IEEE 26th International …, 2023 - ieeexplore.ieee.org
Reinforcement learning (RL) is an experience-driven and data-driven learning method that
can well solve the lane-changing problems. However, because traditional RL methods rely …
can well solve the lane-changing problems. However, because traditional RL methods rely …
Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions
D Bogdoll, J Qin, M Nekolla, A Abouelazm… - arXiv preprint arXiv …, 2024 - arxiv.org
Reinforcement Learning is a highly active research field with promising advancements. In
the field of autonomous driving, however, often very simple scenarios are being examined …
the field of autonomous driving, however, often very simple scenarios are being examined …
Constrained Multi-Agent Reinforcement Learning Policies for Cooperative Intersection Navigation and Traffic Compliance
End to end learning systems are becoming increasingly common in autonomous driving
research, from perception, to planning and control. In particular, distributed reinforcement …
research, from perception, to planning and control. In particular, distributed reinforcement …