Scaffolded Learning of In-place Trotting Gait for a Quadruped Robot with Bayesian Optimization

被引:1
|
作者
Zhai, Keyan [1 ]
Li, Chu'an [1 ]
Rosendo, Andre [1 ]
机构
[1] ShanghaiTech Univ, Sch Informat Sci & Technol, 393 Middle Huaxia Rd, Shanghai 201210, Peoples R China
关键词
Quadruped locomotion; Gait optimization; Parametric search;
D O I
10.1007/978-3-030-95892-3_28
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
During learning trials, systems are exposed to different failure conditions which may break robotic parts before a safe behavior is discovered. Humans contour this problem by grounding their learning to a safer structure/control first and gradually increasing its difficulty. This paper presents the impact of a similar supports in the learning of a stable gait on a quadruped robot. Based on the psychological theory of instructional scaffolding, we provide different support settings to our robot, evaluated with strain gauges, and use Bayesian Optimization to conduct a parametric search towards a stable Raibert controller. We perform several experiments to measure the relation between constant supports and gradually reduced supports during gait learning, and our results show that a gradually reduced support is capable of creating a more stable gait than a support at a fixed height. Although gaps between simulation and reality can lead robots to catastrophic failures, our proposed method combines speed and safety when learning a new behavior.
引用
收藏
页码:365 / 373
页数:9
相关论文
共 50 条
  • [31] An online learning algorithm for adapting leg stiffness and stride angle for efficient quadruped robot trotting
    Aboufazeli, Mahtab
    Samare Filsoofi, Ali
    Gurney, Jason
    Meek, Sanford G. G.
    Mathews, V. John
    FRONTIERS IN ROBOTICS AND AI, 2023, 10
  • [32] Quadruped Robot Creeping Gait Stability Analysis and Optimization Using PSO
    Raheem, Firas A.
    Flayyih, Murtadha Khudhair
    2017 SECOND AL-SADIQ INTERNATIONAL CONFERENCE ON MULTIDISCIPLINARY IN IT AND COMMUNICATION SCIENCE AND APPLICATIONS (AIC-MITCSA), 2017, : 79 - 84
  • [33] Deep Learning Vision System for Quadruped Robot Gait Pattern Regulation
    Cruz Ulloa, Christyan
    Sanchez, Lourdes
    Del Cerro, Jaime
    Barrientos, Antonio
    BIOMIMETICS, 2023, 8 (03)
  • [34] A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
    Zhang, Hanzhong
    Yin, Jibin
    Wang, Haoyang
    SENSORS, 2022, 22 (19)
  • [35] Bayesian Optimization of a Quadruped Robot During 3-Dimensional Locomotion
    Zhu, Jiahui
    Li, Shuting
    Wang, Zhuoli
    Rosendo, Andre
    BIOMIMETIC AND BIOHYBRID SYSTEMS, LIVING MACHINES 2019, 2019, 11556 : 295 - 306
  • [36] Optimum gait for quadruped robot using multi-objective Jaya optimization algorithm
    Huan, Tran Thien
    Anh, Ho Pham Huy
    JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING, 2025, 47 (03)
  • [37] Design of Quadruped Robot Based on Coupling Driving Leg Mechanism and Optimization of Crawling Gait
    Sheng Sha
    Pan Shaopeng
    26TH CHINESE CONTROL AND DECISION CONFERENCE (2014 CCDC), 2014, : 5096 - 5101
  • [38] An MPC-based two-dimensional push recovery of a quadruped robot in trotting gait using its reduced virtual model
    Dini, Navid
    Majd, Vahid Johari
    MECHANISM AND MACHINE THEORY, 2020, 146
  • [39] Learning Impulse-Reduced Gait for Quadruped Robot using CMA-ES
    Ahn, Jaesung
    Im, Euncheol
    Lee, Yisoo
    2023 20TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS, UR, 2023, : 261 - 266
  • [40] Synthesizing the optimal gait of a quadruped robot with soft actuators using deep reinforcement learning
    Ji, Qinglei
    Fu, Shuo
    Tan, Kaige
    Muralidharan, Seshagopalan Thorapalli
    Lagrelius, Karin
    Danelia, David
    Andrikopoulos, Georgios
    Wang, Xi Vincent
    Wang, Lihui
    Feng, Lei
    ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2022, 78