Example-guided learning of stochastic human driving policies using deep reinforcement learning

被引:0
|
作者
Ran Emuna
Rotem Duffney
Avinoam Borowsky
Armin Biess
机构
[1] Ben-Gurion University of the Negev,Department of Industrial Engineering and Management
来源
Neural Computing and Applications | 2023年 / 35卷
关键词
Deep reinforcement learning; Imitation learning; Human driving policies; Gaussian processes;
D O I
暂无
中图分类号
学科分类号
摘要
Deep reinforcement learning has been successfully applied to the generation of goal-directed behavior in artificial agents. However, existing algorithms are often not designed to reproduce human-like behavior, which may be desired in many environments, such as human–robot collaborations, social robotics and autonomous vehicles. Here we introduce a model-free and easy-to-implement deep reinforcement learning approach to mimic the stochastic behavior of a human expert by learning distributions of task variables from examples. As tractable use-cases, we study static and dynamic obstacle avoidance tasks for an autonomous vehicle on a highway road in simulation (Unity). Our control algorithm receives a feedback signal from two sources: a deterministic (handcrafted) part encoding basic task goals and a stochastic (data-driven) part that incorporates human expert knowledge. Gaussian processes are used to model human state distributions and to assess the similarity between machine and human behavior. Using this generic approach, we demonstrate that the learning agent acquires human-like driving skills and can generalize to new roads and obstacle distributions unseen during training.
引用
收藏
页码:16791 / 16804
页数:13
相关论文
共 50 条
  • [1] Example-guided learning of stochastic human driving policies using deep reinforcement learning
    Emuna, Ran
    Duffney, Rotem
    Borowsky, Avinoam
    Biess, Armin
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (23): : 16791 - 16804
  • [2] Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking
    Galljamov, Rustam
    Zhao, Guoping
    Belousov, Boris
    Seyfarth, Andre
    Peters, Jan
    2022 IEEE-RAS 21ST INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2022, : 587 - 593
  • [3] DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
    Peng, Xue Bin
    Abbeel, Pieter
    Levine, Sergey
    van de Panne, Michiel
    ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04):
  • [4] Learning Urban Driving Policies using Deep Reinforcement Learning
    Agarwal, Tanmay
    Arora, Hitesh
    Schneider, Jeff
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 607 - 614
  • [5] EXAMPLE-GUIDED IDENTIFY PRESERVING FACE SYNTHESIS BY METRIC LEARNING
    Wei, Daiyue
    Hu, Xiaoman
    Chen, Keke
    Chan, Patrick P. K.
    PROCEEDINGS OF 2019 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION (ICWAPR), 2019, : 152 - 157
  • [6] Autonomous Highway Driving using Deep Reinforcement Learning
    Nageshrao, Subramanya
    Tseng, H. Eric
    Filev, Dimitar
    2019 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC), 2019, : 2326 - 2331
  • [7] Comfortable Driving by using Deep Inverse Reinforcement Learning
    Kishikawa, Daiko
    Arai, Sachiyo
    2019 IEEE INTERNATIONAL CONFERENCE ON AGENTS (ICA), 2019, : 38 - 43
  • [8] Robust Driving Policy Learning with Guided Meta Reinforcement Learning
    Lee, Kanghoon
    Li, Jiachen
    Isele, David
    Park, Jinkyoo
    Fujimura, Kikuo
    Kochenderfer, Mykel J.
    2023 IEEE 26TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, ITSC, 2023, : 4114 - 4120
  • [9] Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction
    Christen, Sammy
    Stevsic, Stefan
    Hilliges, Otmar
    2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 2161 - 2167
  • [10] Example-guided anthropometric human body modeling
    Zhang, Yuzhe
    Zheng, Jianmin
    Magnenat-Thalmann, Nadia
    VISUAL COMPUTER, 2015, 31 (12): : 1615 - 1631