The invention provides an electric vehicle economical self-adaptive cruise control method and system based on reinforcement learning. The method comprises the steps that a Markov model of a car-following system is established; according to an Actor-Critic algorithm in reinforcement learning, a self-adaptive cruise controller is designed; and according to a speed control signal of the self-adaptive cruise controller, converting the speed control signal into the acceleration/deceleration pedal clamping opening degree according to the inverse dynamic model, and controlling the vehicle to safely follow the front vehicle. The front vehicle can be safely, comfortably and stably followed, the collision behavior is avoided, and the self-adaptive capacity is good. Compared with a control strategy which only considers driving safety, the state of charge of the battery is improved within the same driving period.
本发明提供了一种基于强化学习的电动汽车经济性自适应巡航控制方法及系统,所述方法包括:建立跟驰系统的马尔科夫模型;根据强化学习中Actor‑Critic算法,设计自适应巡航控制器;根据自适应巡航控制器的速度控制信号,根据逆动力学模型转化为加速/减速踏板卡开度,控制车辆安全跟随前车。本发明能够实现安全、舒适、平稳的跟随前车,避免碰撞行为发生,自适应能力较好。与只考虑驾驶安全的控制策略相比,在相同驾驶周期内,电池荷电状态有所提高。
Electric vehicle economical self-adaptive cruise control method and system based on reinforcement learning
一种基于强化学习的电动汽车经济性自适应巡航控制方法及系统
2022-07-22
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
Economical self-adaptive cruise control method for electric vehicle based on multi-step DDQN
European Patent Office | 2023
|Adaptive cruise control method and system based on deep reinforcement learning
European Patent Office | 2023
|Personalized adaptive cruise system based on deep reinforcement learning and control method thereof
European Patent Office | 2023
|