Continuous Control for Automated Lane Change Behavior Based on Deep Deterministic Policy Gradient Algorithm

TL;DR

This paper develops a continuous control method for automated lane change using Deep Deterministic Policy Gradient, enabling smooth and safe lane changes in simulation without prior environment knowledge.

Contribution

It introduces a continuous action space approach for lane change control with DDPG, improving over discrete methods and demonstrating stable, successful lane changes in diverse scenarios.

Findings

RL agent achieves 100% success rate in simulation

Continuous control improves lane change smoothness

Method does not require prior environment knowledge

Abstract

Lane change is a challenging task which requires delicate actions to ensure safety and comfort. Some recent studies have attempted to solve the lane-change control problem with Reinforcement Learning (RL), yet the action is confined to discrete action space. To overcome this limitation, we formulate the lane change behavior with continuous action in a model-free dynamic driving environment based on Deep Deterministic Policy Gradient (DDPG). The reward function, which is critical for learning the optimal policy, is defined by control values, position deviation status, and maneuvering time to provide the RL agent informative signals. The RL agent is trained from scratch without resorting to any prior knowledge of the environment and vehicle dynamics since they are not easy to obtain. Seven models under different hyperparameter settings are compared. A video showing the learning progress of the driving behavior is available. It demonstrates the RL vehicle agent initially runs out of road boundary frequently, but eventually has managed to smoothly and stably change to the target lane with a success rate of 100% under diverse driving situations in simulation.