Abstract
In an autonomous vehicle, the lane following algorithm is an important component, which is a basic function of autonomous driving. However, the existing lane following system has a few shortcomings: first, the control method it adopts requires an accurate system model, and different vehicles have different parameters, which needs a lot of parameter calibration work. The second is that it may fail on road sections where the lateral acceleration requirements of vehicles are large, such as large curves. Third, its decision-making system is defined based on rules, which has disadvantages: it is difficult to formulate; human subjective factors cannot guarantee objectivity; coverage is difficult to guarantee. In recent years, the deep deterministic policy gradient (DDPG) algorithm has been widely used in the field of autonomous driving due to its strong nonlinear fitting ability and generalization performance. However, the DDPG algorithm has overestimated state action values and large cumulative errors, low training efficiency and other issues. Therefore, this paper improves the DDPG algorithm based on the double critic networks and priority experience replay mechanism. Then this paper proposes a lane following method based on this algorithm. Experiment shows that the algorithm can achieve excellent following results under various road conditions.
Highlights
Lane following is one of the most important autonomous driving subsystems
In order to solve this problem, the authors in [22] propose the deep deterministic policy gradient (DDPG) algorithm, which is an algorithm based on direct policy search that can directly output continuous action values, which is very suitable for continuous control environments
The angle with the lane axis is reduced by 40%, and the distance from the road centerline is reduced by 49%, indicating that the algorithm in this paper is processing the lane following task is significantly better than the DDPG algorithm
Summary
Lane following is one of the most important autonomous driving subsystems. Only after successfully implementing the lane following function can other advanced subsystems of autonomous driving such as obstacle avoidance and car following be further developed [1]. In order to solve this problem, the authors in [22] propose the DDPG algorithm, which is an algorithm based on direct policy search that can directly output continuous action values, which is very suitable for continuous control environments. The author applied it to lane following and achieved good results in the TORCS environment. A project that requires a lot of manpower and material resources will cause much waste of resources For dealing with this problem, this paper proposes double critic networks and priority experience replay deep deterministic policy gradient (DCPER-DDPG) algorithm. This paper proposes a lane following algorithm architecture based on deep reinforcement learning; secondly, designs the reward function, exploration strategy, and improved DDPG algorithm; the algorithm proposed in this paper is tested and verified on the TORCS simulation platform
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
