The invention provides a reinforcement learning automatic driving decision-making method and device based on trajectory prediction, and relates to the technical field of automatic driving. The method comprises the following steps: acquiring driving track time sequence data of an automatic driving vehicle and other vehicles around the automatic driving vehicle in a historical time period; inputting the driving track time sequence data into a trained Transformer model so as to predict the driving tracks of other vehicles around the automatic driving vehicle and obtain corresponding track prediction information; and adding the trajectory prediction information into a state space corresponding to a trained reinforcement learning model to obtain a target state space, so that the reinforcement learning model performs an automatic driving decision based on the target state space. Therefore, the driving track prediction information of the other vehicles is added into the state information of the reinforcement learning decision, so that the possibility that the automatic driving vehicle collides with the other vehicles is reduced, and the purpose of improving the passing success rate of the automatic driving decision is achieved.
本申请提供一种基于轨迹预测的强化学习自动驾驶决策方法及装置,涉及自动驾驶技术领域。其中方法包括:获取在历史时间段内的自动驾驶车辆与其周围其他车辆的行驶轨迹时序数据;将所述驾驶轨迹时序数据输入训练好的Transformer模型,以对自动驾驶车辆周围其他车辆的行驶轨迹进行预测,得到相应的轨迹预测信息;将所述轨迹预测信息加入到训练好的强化学习模型对应的状态空间中,得到目标状态空间,以使所述强化学习模型基于所述目标状态空间进行自动驾驶决策。可见,本申请在强化学习决策的状态信息中加入其他车辆的行车轨迹预测信息,从而减小自动驾驶车辆与其他车辆发生碰撞的可能性,达到提高自动驾驶决策的通行成功率的目的。
Reinforcement learning automatic driving decision-making method and device based on trajectory prediction
一种基于轨迹预测的强化学习自动驾驶决策方法及装置
2024-08-20
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 |
Automatic driving decision-making method based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving vehicle microscopic decision-making method based on reinforcement learning
European Patent Office | 2020
|Automatic driving behavior decision-making method based on deep reinforcement learning
European Patent Office | 2020
|Automatic driving behavior 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
|