The invention discloses an automatic driving vehicle microcosmic decision-making method based on reinforcement learning. According to the method, a reinforcement learning A3C algorithm is adopted, driving behaviors are output by an Actor network, the flexibility is high, and the complexity of logic judgment is not affected by state space and behavior space. According to the method, a two-stage training solving process is adopted. In the first stage, an automatic driving microcosmic decision model suitable for all road sections is obtained through training so as to guarantee driving safety. Inthe second stage, the overall model in the first stage is deployed to each road section, and each road section trains a single-road-section model on the basis of the overall model and has transportability. Meanwhile, the continuous training of the second stage enables the method to adapt to the influence of various real-time factors. Finally, distributed communication architecture based on a realInternet of Vehicles system structure is elaborated, and distributed calculation in the solving process can be completed, so that the method can adapt to different road features and dynamic driving environments, and has wide applicability and robustness.
本发明公开了一种基于强化学习的自动驾驶车辆微观决策方法。所述方法采用强化学习的A3C算法,驾驶行为由Actor网络输出,灵活性强,判断逻辑的复杂度不受状态空间与行为空间大小的影响。所述方法采用了两阶段的训练求解过程。第一阶段训练得到一个适用所有路段的自动驾驶微观决策模型,以保证驾驶安全。第二阶段将第一阶段的整体模型部署到每条路段,各路段在此基础上各自训练单路段模型,具有可移植性。同时,第二阶段的持续训练使所述方法能够适应各种实时因素的影响。最后阐述了基于真实车联网系统结构的分布式通信架构,能够完成求解过程中的分布式计算,因此,所述方法能够适应不同的道路特征和动态的驾驶环境,具有广泛的适用性和鲁棒性。
Automatic driving vehicle microscopic decision-making method based on reinforcement learning
基于强化学习的自动驾驶车辆微观决策方法
2020-10-30
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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Automatic driving vehicle overtaking decision-making method based on deep reinforcement learning
European Patent Office | 2022
|Automatic driving decision-making method based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving decision-making system based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving behavior decision-making method based on deep reinforcement learning
European Patent Office | 2020
|Automatic driving decision-making method based on rule-assisted reinforcement learning
European Patent Office | 2023
|