A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers
This work addresses the challenge of reliable lane changing for autonomous vehicles, offering a method that improves over rule-based models, though it appears incremental as it builds on existing deep Q-learning techniques.
The authors tackled the problem of automated lane change maneuvers by proposing a reinforcement learning approach that learns smooth and efficient driving policies, achieving successful performance in diverse and unforeseen scenarios through extensive simulations.
Lane change is a crucial vehicle maneuver which needs coordination with surrounding vehicles. Automated lane changing functions built on rule-based models may perform well under pre-defined operating conditions, but they may be prone to failure when unexpected situations are encountered. In our study, we proposed a Reinforcement Learning based approach to train the vehicle agent to learn an automated lane change behavior such that it can intelligently make a lane change under diverse and even unforeseen scenarios. Particularly, we treated both state space and action space as continuous, and designed a Q-function approximator that has a closed- form greedy policy, which contributes to the computation efficiency of our deep Q-learning algorithm. Extensive simulations are conducted for training the algorithm, and the results illustrate that the Reinforcement Learning based vehicle agent is capable of learning a smooth and efficient driving policy for lane change maneuvers.