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
  • [31] OPPOSITION-BASED LEARNING PARTICLE SWARM OPTIMIZATION OF RUNNING GAIT FOR HUMANOID ROBOT
    Yang, Liang
    Song Xijia
    Deng, Chunjian
    INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, 2015, 8 (02): : 1162 - 1179
  • [32] Multipolicy Robot-Following Model Based on Reinforcement Learning
    Yu, Ning
    Nan, Lin
    Ku, Tao
    SCIENTIFIC PROGRAMMING, 2021, 2021
  • [33] Cognitive Emotional Interaction Model of Robot Based on Reinforcement Learning
    Huang Hongcheng
    Li Jing
    Hu Min
    Tao Yang
    Kou Lan
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2021, 43 (06) : 1781 - 1788
  • [34] Model Predictive Control of Quadruped Robot Based on Reinforcement Learning
    Zhang, Zhitong
    Chang, Xu
    Ma, Hongxu
    An, Honglei
    Lang, Lin
    APPLIED SCIENCES-BASEL, 2023, 13 (01):
  • [35] Cognitive Emotional Interaction Model of Robot Based on Reinforcement Learning
    Huang, Hongcheng
    Li, Jing
    Hu, Min
    Tao, Yang
    Kou, Lan
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2021, 43 (06): : 1781 - 1788
  • [36] Safe Robot Execution in Model-Based Reinforcement Learning
    Martinez, David
    Alenya, Guillem
    Torras, Carme
    2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 6422 - 6427
  • [37] Facial Expression Imitation Method for Humanoid Robot Based on Smooth-Constraint Reversed Mechanical Model (SRMM)
    Huang, Zhong
    Ren, Fuji
    Hu, Min
    Chen, Sugen
    IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2020, 50 (06) : 538 - 549
  • [38] An Adaptive LIPM-based Dynamic Walk using Model Parameter Optimization on Humanoid Robots
    Seekircher, Andreas
    Visser, Ubbo
    KUNSTLICHE INTELLIGENZ, 2016, 30 (3-4): : 233 - 244
  • [39] Motion segmentation and recognition for imitation learning and influence of bias for learningwalking motion of humanoid robot based on human demonstrated motion
    Department of Human and Artificial Intelligent Systems, Graduate School of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui, Fukui
    910-8507, Japan
    不详
    910-8507, Japan
    不详
    535-8585, Japan
    J. Adv. Comput. Intell. Intelligent Informatics, 4 (532-543):
  • [40] Safe dynamic optimization of automatic generation control via imitation-based reinforcement learning
    Zhang, Zhiyuan
    Wu, Yongjun
    Hao, Zhenkun
    Song, Minghui
    Yu, Peipei
    Frontiers in Energy Research, 2024, 12