Benchmarking the Full-Order Model Optimization Based Imitation in the Humanoid Robot Reinforcement Learning Walk

被引:0
|
作者
Chaikovskaya, Ekaterina [1 ]
Minashina, Inna [1 ]
Litvinenko, Vladimir [1 ]
Davydenko, Egor [1 ]
Makarov, Dmitry [1 ,2 ]
Danik, Yulia [1 ,2 ]
Gorbachev, Roman [1 ]
机构
[1] Moscow Inst Phys & Technol, Moscow, Russia
[2] Russian Acad Sci, Fed Res Ctr Comp Sci & Control, Moscow, Russia
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
When a gait of a bipedal robot is developed using deep reinforcement learning, reference trajectories may or may not be used. Each approach has its advantages and disadvantages, and the choice of method is up to the control developer. This paper investigates the effect of reference trajectories on locomotion learning and the resulting gaits. We implemented three gaits of a full-order anthropomorphic robot model with different reward imitation ratios, provided sim-to-sim control policy transfer, and compared the gaits in terms of robustness and energy efficiency. In addition, we conducted a qualitative analysis of the gaits by interviewing people, since our task was to create an appealing and natural gait for a humanoid robot. According to the results of the experiments, the most successful approach was the one in which the average value of rewards for imitation and adherence to command velocity per episode remained balanced throughout the training. The gait obtained with this method retains naturalness (median of 3.6 according to the user study) compared to the gait trained with imitation only (median of 4.0), while remaining robust close to the gait trained without reference trajectories.
引用
收藏
页码:206 / 211
页数:6
相关论文
共 50 条
  • [41] A full freedom pose measurement method for industrial robot based on reinforcement learning algorithm
    Xinghua Lu
    Yunsheng Chen
    Ziyue Yuan
    Soft Computing, 2021, 25 : 13027 - 13038
  • [42] A full freedom pose measurement method for industrial robot based on reinforcement learning algorithm
    Lu, Xinghua
    Chen, Yunsheng
    Yuan, Ziyue
    SOFT COMPUTING, 2021, 25 (20) : 13027 - 13038
  • [43] Energy model based loss-minimized speed control of induction motor with a full-order observer
    Mannan, Mohammad Abdul
    Murata, Toshiaki
    Tamura, Junji
    Tsuchiya, Takeshi
    IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2006, 1 (01) : 35 - 44
  • [44] Robot path planner based on deep reinforcement learning and the seeker optimization algorithm
    Xing, Xiangrui
    Ding, Hongwei
    Liang, Zhuguan
    Li, Bo
    Yang, Zhijun
    MECHATRONICS, 2022, 88
  • [45] Impedance control and parameter optimization of surface polishing robot based on reinforcement learning
    Ding, Yufeng
    Zhao, JunChao
    Min, Xinpu
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE, 2023, 237 (1-2) : 216 - 228
  • [46] Inference Model for Heterogeneous Robot Team Configuration based on Reinforcement Learning
    Sun, Xueqing
    Mao, Tao
    Ray, Laura E.
    2009 IEEE INTERNATIONAL CONFERENCE ON TECHNOLOGIES FOR PRACTICAL ROBOT APPLICATIONS (TEPRA 2009), 2009, : 55 - 60
  • [47] Model-based Imitation Learning for Real-time Robot Navigation in Crowds
    Moder, Martin
    Oezgan, Fatih
    Pauli, Josef
    2023 32ND IEEE INTERNATIONAL CONFERENCE ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION, RO-MAN, 2023, : 513 - 519
  • [48] Full Vehicle Trajectory Planning Model for Urban Traffic Control Based on Imitation Learning
    Ying, Jun
    Feng, Yiheng
    TRANSPORTATION RESEARCH RECORD, 2022, 2676 (07) : 186 - 198
  • [49] On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
    Zhang, Baohe
    Rajan, Raghu
    Pineda, Luis
    Lambert, Nathan
    Biedenkapp, Andre
    Chua, Kurtland
    Hutter, Frank
    Calandra, Roberto
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [50] Real-time walking pattern optimization for humanoid robot based on model predictive control
    Ding J.-T.
    He J.
    Li L.-Z.
    Xiao X.-H.
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2019, 53 (10): : 1843 - 1851