Vision-Based Autonomous Driving: A Model Learning Approach

被引:0
|
作者
Baheri, Ali [1 ]
Kolmanovsky, Ilya [2 ]
Girard, Anouck [2 ]
Tseng, H. Eric [3 ]
Filev, Dimitar [3 ]
机构
[1] West Virginia Univ, Dept Aerosp & Mech Engn, Morgantown, WV 26505 USA
[2] Univ Michigan, Dept Aerosp Engn, Ann Arbor, MI 48109 USA
[3] Ford Res & Innovat Ctr, 2101 Village Rd, Dearborn, MI 48124 USA
关键词
GO;
D O I
10.23919/acc45564.2020.9147510
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy exploiting the learned model to identify the action to take at each time-step. To build a model for the environment, we leverage several deep learning algorithms. To that end, first we train a variational autoencoder to encode the input image into an abstract latent representation. We then utilize a recurrent neural network to predict the latent representation of the next frame and handle temporal information. Finally, we utilize an evolutionary-based reinforcement learning algorithm to train a controller based on these latent representations to identify the action to take. We evaluate our approach in CARLA, a high-fidelity urban driving simulator, and conduct an extensive generalization study. Our results demonstrate that our approach outperforms several previously reported approaches in terms of the percentage of successfully completed episodes for a lane keeping task.
引用
收藏
页码:2520 / 2525
页数:6
相关论文
共 50 条
  • [21] Scaling Vision-based End-to-End Autonomous Driving with Multi-View Attention Learning
    Xiao, Yi
    Codevilla, Felipe
    Porres, Diego
    Lopez, Antonio M.
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IROS, 2023, : 1586 - 1593
  • [22] Vision-based driving assistance
    Broggi, A
    IEEE INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 1998, 13 (06): : 22 - 23
  • [23] Vision-Based Autonomous Navigation Using Supervised Learning Techniques
    Souza, Jefferson R.
    Pessin, Gustavo
    Osorio, Fernando S.
    Wolf, Denis F.
    ENGINEERING APPLICATIONS OF NEURAL NETWORKS, PT I, 2011, 363 : 11 - 20
  • [24] A Color Vision-Based Lane Tracking System for Autonomous Driving on Unmarked Roads
    Miguel Angel Sotelo
    Francisco Javier Rodriguez
    Luis Magdalena
    Luis Miguel Bergasa
    Luciano Boquete
    Autonomous Robots, 2004, 16 : 95 - 116
  • [25] Reconstruction-Based Adversarial Attack Detection in Vision-Based Autonomous Driving Systems
    Hussain, Manzoor
    Hong, Jang-Eui
    MACHINE LEARNING AND KNOWLEDGE EXTRACTION, 2023, 5 (04): : 1589 - 1611
  • [26] A sonar approach to obstacle detection for a vision-based autonomous wheelchair
    Del Castillo, Guillermo
    Skaar, Steven
    Cardenas, Antonio
    Fehr, Linda
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2006, 54 (12) : 967 - 981
  • [27] Efficient GEMM Implementation for Vision-Based Object Detection in Autonomous Driving Applications
    Guerrouj, Fatima Zahra
    Florez, Sergio Rodriguez
    Abouzahir, Mohamed
    El Ouardi, Abdelhafid
    Ramzi, Mustapha
    JOURNAL OF LOW POWER ELECTRONICS AND APPLICATIONS, 2023, 13 (02)
  • [28] A Vision-based Forward Driving Vehicle Velocity Estimation Algorithm for Autonomous Vehicles
    Kang, Hosun
    Lee, Jangmyung
    2021 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM), 2021, : 492 - 497
  • [29] A comparative study of vision-based lateral control strategies for autonomous highway driving
    Taylor, CJ
    Kosecká, J
    Blasi, R
    Malik, J
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 1999, 18 (05): : 442 - 453
  • [30] A Novel Vision-Based Approach for Autonomous Space Navigation Systems
    Bevilacqua, Alessandro
    Gherardi, Alessandro
    Carozza, Ludovico
    ADVANCES IN VISUAL COMPUTING, PT 2, PROCEEDINGS, 2009, 5876 : 837 - 846