Vehicle speed tracking in bench test based on DDPG

As an important means of vehicle test, powertrain bench test can complete the performance test of vehicles under different working conditions and road conditions without complex test site. Therefore, at present, the automotive industry usually uses indoor bench test to replace some outdoor real vehicle tests. In order to improve the accuracy of bench test, a speed tracking control algorithm based on DDGP (deep deterministic policy gradient) algorithm is constructed, and the action space, state space and reward function are designed. At the same time, Bayesian algorithm is used to optimize the hyperparameters of DDPG algorithm. The simulation results show that the algorithm can effectively control the pedal for speed tracking control.