Modified DDPG car-following model with a real-world human driving experience with CARLA simulator

Abstract

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 Operating System (ROS). For evaluation, we designed different driving scenarios to compare the proposed two-stage DRL car-following agent with other agents. After extracting the "good" behavior from the human driver, the agent becomes more efficient and reasonable, which makes this autonomous agent more suitable for Human-Robot Interaction (HRI) traffic.

References in corpus (3)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Estimating Acceleration and Lane-Changing Dynamics Based on NGSIM Trajectory Data
• Formulation and validation of a car-following model based on deep reinforcement learning

Cited by in corpus (4)

• FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling
• Autonomous Driving Small-Scale Cars: A Survey of Recent Development
• A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Driving
• Vision-based DRL Autonomous Driving Agent with Sim2Real Transfer