A Deep Reinforcement Learning Based Motion Cueing Algorithm for Vehicle Driving Simulation

被引:0
|
作者
Scheidel, Hendrik [1 ]
Asadi, Houshyar [1 ]
Bellmann, Tobias [2 ]
Seefried, Andreas [2 ]
Mohamed, Shady [1 ]
Nahavandi, Saeid [1 ]
机构
[1] Deakin Univ, Inst Intelligent Syst Res & Innovat, Geelong, Vic 3216, Australia
[2] German Aerosp Ctr, Inst Syst Dynam & Control, D-82234 Wessling, Germany
关键词
Trajectory; Training; Prediction algorithms; Artificial neural networks; Real-time systems; Training data; Filtering; Motion cueing algorithm; deep reinforcement learning; proximal policy optimization; machine learning; artificial neural network; motion simulator; WASHOUT FILTER; FUZZY-LOGIC; PLATFORM; GAME; GO;
D O I
10.1109/TVT.2024.3375941
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Motion cueing algorithms (MCA) are used to control the movement of motion simulation platforms (MSP) to reproduce the motion perception of a real vehicle driver as accurately as possible without exceeding the limits of the workspace of the MSP. Existing approaches either produce non-optimal results due to filtering, linearization, or simplifications, or the computational time required exceeds the real-time requirements of a closed-loop application. This work presents a new solution to the motion cueing problem, where instead of a human designer specifying the principles of the MCA, an artificial intelligence (AI) learns the optimal motion by trial and error in interaction with the MSP. To achieve this, a well-established deep reinforcement learning (RL) algorithm is applied, where an agent interacts with an environment, allowing him to directly control a simulated MSP to obtain feedback on its performance. The RL algorithm used is proximal policy optimization (PPO), where the value function and the policy corresponding to the control strategy are both learned and mapped in artificial neural networks (ANN). This approach is implemented in Python and the functionality is demonstrated by the practical example of pre-recorded lateral maneuvers. The subsequent validation shows that the RL algorithm is able to learn the control strategy and improve the quality of the immersion compared to an established method. Thereby, the perceived motion signals determined by a model of the vestibular system are more accurately reproduced, and the resources of the MSP are used more economically.
引用
收藏
页码:9696 / 9705
页数:10
相关论文
共 50 条
  • [1] Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning
    Liu, Yunzhuo
    Zhang, Ruoning
    Zhou, Shijie
    [J]. ELECTRONICS, 2023, 12 (24)
  • [2] Deep Inverse Reinforcement Learning for Behavior Prediction in Autonomous Driving: Accurate Forecasts of Vehicle Motion
    Fernando, Tharindu
    Denman, Simon
    Sridharan, Sridha
    Fookes, Clinton
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2021, 38 (01) : 87 - 96
  • [3] Autonomous Vehicle Driving Path Control with Deep Reinforcement Learning
    Tiong, Teckchai
    Saad, Ismail
    Teo, Kenneth Tze Kin
    bin Lago, Herwansyah
    [J]. 2023 IEEE 13TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE, CCWC, 2023, : 84 - 92
  • [4] AMI: Adaptive Motion Imitation Algorithm Based on Deep Reinforcement Learning
    Taghavi, Nazita
    Alqatamin, Moath H. A.
    Popa, Dan O.
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022), 2022,
  • [5] Model Predictive Control based Motion Cueing Algorithm for Driving Simulator
    Hameed, Ayesha
    Abadi, Ali Soltani Sharif
    Ordys, Andrzej
    [J]. JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING, 2024, 33 (05) : 607 - 626
  • [6] A Review of Deep Learning-Based Vehicle Motion Prediction for Autonomous Driving
    Huang, Renbo
    Zhuo, Guirong
    Xiong, Lu
    Lu, Shouyi
    Tian, Wei
    [J]. SUSTAINABILITY, 2023, 15 (20)
  • [7] Model-based predictive motion cueing strategy for vehicle driving simulators
    Dagdelen, Mehmet
    Reymond, Gilles
    Kemeny, Andras
    Bordier, Marc
    Maizi, Nadia
    [J]. CONTROL ENGINEERING PRACTICE, 2009, 17 (09) : 995 - 1003
  • [8] Lateral Motion Control for Obstacle Avoidance in Autonomous Driving Based on Deep Reinforcement Learning
    Liao, Yaping
    Yu, Guizhen
    Chen, Peng
    Zhou, Bin
    Li, Han
    [J]. 2023 IEEE 26TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, ITSC, 2023, : 5229 - 5234
  • [9] Local motion simulation using deep reinforcement learning
    Xu, Dong
    Huang, Xiao
    Li, Zhenlong
    Li, Xiang
    [J]. TRANSACTIONS IN GIS, 2020, 24 (03) : 756 - 779
  • [10] New motion cueing algorithm for driving simulator based on variant harmonic wavelet
    X. M. Gong
    X. H. Li
    S. A. Wang
    [J]. International Journal of Automotive Technology, 2015, 16 : 117 - 126