The invention discloses an automatic driving decision planning method based on deep reinforcement learning and deep learning. The method is realized based on a trained deep reinforcement learning network. The deep reinforcement learning network comprises an Actor network, a TIN network, a Critic network and a vehicle trajectory prediction network; according to the method, a decision planning algorithm integrating task importance and a vehicle trajectory planning method is introduced on the basis of deep reinforcement learning, the importance degree of a driving environment state to a current action decision is considered, a network structure based on the task importance is established, and gradual updating in a training process is realized; on the planning level, based on trajectory prediction, a reward function is introduced to be fused with environment information in a network, the traveling decision effect is shorter in passing time and higher in safety, the convergence speed and the convergence effect are improved compared with an existing algorithm, the efficiency, safety and comfort of a decision planning system are improved, and the method is suitable for large-scale popularization and application. And a scheme is provided for research on an automatic driving road driving-out decision-making mechanism, evaluation and the like.

    本发明公开了一种基于深度强化学习和深度学习的自动驾驶决策规划方法,其基于经过训练的深度强化学习网络实现;深度强化学习网络包括Actor网络、TIN网络、Critic网络和车辆轨迹预测网络;该方法在深度强化学习的基础上引入了任务重要性与车辆轨迹规划方法融合的决策规划算法,考虑了驾驶环境状态对当前动作决策的重要程度,并建立基于任务重要性的网络结构,实现在训练进程中逐步更新;在规划层次基于轨迹预测,引入奖励函数与网络中环境信息融合,实现在行驶决策效果上具有通行时间更短,安全性更高,相比现有算法提高了收敛速度和收敛效果,提升了决策规划系统的效率、安全性和舒适性,为自动驾驶公路驶出决策机理和评估等研究提供一种方案。


    Access

    Download


    Export, share and cite



    Title :

    Automatic driving decision planning method based on deep reinforcement learning and deep learning


    Additional title:

    一种基于深度强化学习和深度学习的自动驾驶决策规划方法


    Contributors:
    YANG LU (author) / ZHANG HAO (author) / TAN YANSONG (author) / GAO LILAN (author) / WANG YIQUAN (author) / GE JIANLONG (author)

    Publication date :

    2024-11-15


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Automatic driving decision-making method based on deep reinforcement learning

    LIU CHENGQI / LIU SHAOWEIHUA / ZHANG YUJIE et al. | European Patent Office | 2024

    Free access

    Automatic driving decision planning method based on deep reinforcement learning and A-Star algorithm

    YAO BAOZHEN / YANG WEICHEN / JIANG MENG et al. | European Patent Office | 2024

    Free access

    Automatic driving behavior decision-making method based on deep reinforcement learning

    YANG MINGZHU / LIU XIANGWEI / LI ZHUOLUO | European Patent Office | 2020

    Free access

    Automatic driving decision-making system based on deep reinforcement learning

    ZHENG XIAOYAO / YAO QINGHE / ZHANG JIANPENG et al. | European Patent Office | 2024

    Free access

    Automatic driving behavior decision-making method based on deep reinforcement learning

    ZOU JUNYI / WANG HAIXIN | European Patent Office | 2024

    Free access