Gait Synthesis of a Hybrid Legged Robot Using Reinforcement Learning

被引:0
|
作者
dos Santos, Jeeves Lopes [1 ]
Nascimento Junior, Cairo Lucio [1 ]
机构
[1] Inst Tecnol Aeronaut, Div Elect Engn, BR-12228900 Sao Jose Dos Campos, SP, Brazil
来源
2015 9TH ANNUAL IEEE INTERNATIONAL SYSTEMS CONFERENCE (SYSCON) | 2015年
关键词
Walking Machine; Hybrid Legged Robot; Reinforcement Learning; Learning Automata; Gait Synthesis;
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This article is concerned with the gait synthesis problem of a hybrid robot (in this case, a four-legged robot with free wheels on its feet) considering multiple criteria. It is assumed that the position of each leg actuator over time is described by a periodic function with parameters that are determined using the learning automata reinforcement learning algorithm. Analysis of the robot morphology is used to group similar legs and decrease the number of actuator functions that must be determined. MATLAB/Simulink/Sim Mechanics Toolbox are used to simulate the robot gait. The simulated robot response is evaluated by the reinforcement learning algorithm considering: 1) the robot frontal speed, 2) the "smoothness" of the robot movements, 3) the largest torque required by all leg actuators, and 4) the robot energy consumption. When the reinforcement learning algorithm converges to a good solution, it is applied to the real robot which was built using the Bioloid Comprehensive Kit, an educational robot kit manufactured by ROBOTIS. The responses of the simulated and real robot are then compared and are shown to be similar.
引用
收藏
页码:439 / 444
页数:6
相关论文
共 50 条
  • [41] Reinforcement Learning of Single Legged Locomotion
    Fankhauser, Peter
    Hutter, Marco
    Gehring, Christian
    Bloesch, Michael
    Hoepflinger, Mark A.
    Siegwart, Roland
    2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2013, : 188 - 193
  • [42] Gait control of a six-legged robot on unlevel terrain using a cognitive architecture
    Janrathitikarn, Oranuj
    Long, Lyle N.
    2008 IEEE AEROSPACE CONFERENCE, VOLS 1-9, 2008, : 70 - 78
  • [43] Insect - computer hybrid legged robot with user-adjustable speed, step length and walking gait
    Cao, Feng
    Zhang, Chao
    Choo, Hao Yu
    Sato, Hirotaka
    JOURNAL OF THE ROYAL SOCIETY INTERFACE, 2016, 13 (116)
  • [44] Reinforcement Learning for Bipedal Gait with MAX-E2 Humanoid Robot
    Yanguas-Rojas, David
    Mojica-Nava, Eduardo
    Cardenas, Alben
    INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS, 2022, 19 (05)
  • [45] Reinforcement Learning Assist-as-needed Control for Robot Assisted Gait Training
    Zhang, Yufeng
    Li, Shuai
    Nolan, Karen J.
    Zanotto, Damiano
    2020 8TH IEEE RAS/EMBS INTERNATIONAL CONFERENCE FOR BIOMEDICAL ROBOTICS AND BIOMECHATRONICS (BIOROB), 2020, : 785 - 790
  • [46] Robot control optimization using reinforcement learning
    Natl Chiao Tung Univ, Hsinchu, Taiwan
    J Intell Rob Syst Theor Appl, 3 (221-238):
  • [47] Robot Control Optimization Using Reinforcement Learning
    Kai-Tai Song
    Wen-Yu Sun
    Journal of Intelligent and Robotic Systems, 1998, 21 : 221 - 238
  • [48] Robot control optimization using reinforcement learning
    Song, KT
    Sun, WY
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 1998, 21 (03) : 221 - 238
  • [49] Combining Prior Knowledge and Reinforcement Learning for Parallel Telescopic-Legged Bipedal Robot Walking
    Xue, Jie
    Huangfu, Jiaqi
    Hou, Yunfeng
    Mou, Haiming
    MATHEMATICS, 2025, 13 (06)
  • [50] Learning an Efficient Gait Cycle of a Biped Robot Based on Reinforcement Learning and Artificial Neural Networks
    Gil, Cristyan R.
    Calvo, Hiram
    Sossa, Humberto
    APPLIED SCIENCES-BASEL, 2019, 9 (03):