Modified DDPG car-following model with a real-world human driving experience with CARLA simulator. (arXiv:2112.14602v3 [cs.RO] UPDATED)

In the autonomous driving field, fusion of human knowledge into Deep
Reinforcement Learning (DRL) is often based on the human demonstration recorded
in a simulated environment. This limits the generalization and the feasibility
of application in real-world traffic. We propose a two-stage DRL method to
train a car-following agent, that modifies the policy by leveraging the
real-world human driving experience and achieves performance superior to the
pure DRL agent. Training a DRL agent is done within CARLA framework with Robot …

arxiv ddpg driving experience human