The invention discloses an unmanned vehicle trajectory prediction method based on fuzzy inverse reinforcement learning. The method comprises the following steps: calculating trajectory features, introducing fuzzy logic to carry out inverse reinforcement learning to find an optimal weight vector, and carrying out optimal trajectory prediction simulation. According to the method, the optimal weight vector is obtained by processing the driving track data of the unmanned vehicle and the actual data of a human driver and combining fuzzy logic processing and training an inverse reinforcement learning model, so that the optimal driving track of the unmanned vehicle is calculated in a limited track. According to the invention, the problems of poor adaptability to the complex environment and low decision accuracy in the driving strategy process of the unmanned vehicle in the prior art are solved, and the driving strategy efficiency and safety of the unmanned vehicle in the actual road environment are remarkably improved. And a fuzzy inverse reinforcement learning method is introduced, so that the unmanned vehicle can better learn a driving strategy of a human driver, and a more intelligent and safer automatic driving function is realized.

    本发明公开了一种基于模糊逆强化学习的无人车轨迹预测方法,包括如下步骤:计算轨迹特征、引入模糊逻辑进行逆强化学习来寻找最优权重向量、最优轨迹预测仿真。本发明主要通过处理无人车行驶轨迹数据及人类驾驶员的实际数据,结合模糊逻辑处理,训练逆强化学习模型,得到最优权重向量,从而在有限轨迹中计算出无人车的行驶最优轨迹。本发明解决了现有技术中无人车在行驶策略过程中对复杂环境适应性差和决策准确性低的问题,显著提高了无人车在实际道路环境中的行驶策略效率和安全性。引入模糊逆强化学习方法,使得无人车能够更好地学习人类驾驶员的行驶策略,从而实现更智能和安全的自动驾驶功能。


    Access

    Download


    Export, share and cite



    Title :

    Unmanned vehicle trajectory prediction method based on fuzzy inverse reinforcement learning


    Additional title:

    基于模糊逆强化学习的无人车轨迹预测方法


    Contributors:
    LIU JING (author) / HAN YONG (author) / HOU RONGBIN (author) / SHI JIANQI (author) / SUN HAIYING (author)

    Publication date :

    2024-11-19


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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




    IRLSOT: Inverse reinforcement learning for scene‐oriented trajectory prediction

    He, Caizhen / Chen, Lanping / Xu, Liming et al. | Wiley | 2022

    Free access



    Unmanned vehicle group forming method based on trajectory prediction

    CHENG JIUJUN / HOU MENGNAN / MAO QICHAO | European Patent Office | 2024

    Free access