RoboCup3D仿真机器人步态优化研究

doi:10.3969/j.issn.1006-2475.2018.03.004

计算机与现代化

RoboCup3D仿真机器人步态优化研究

(1.河海大学计算机与信息学院,江苏南京210098;2.常州工学院计算机信息工程学院,江苏常州213002)

收稿日期:2017-09-21 出版日期:2018-04-03 发布日期:2018-04-03
作者简介:何荣义(1992-),男,江苏兴化人,河海大学计算机与信息学院硕士研究生,研究方向:双足机器人步态优化; 李春光(1976-),男,湖北武汉人,常州工学院计算机信息工程学院副教授,博士,研究方向:双足机器人步态规划,机器人蜂拥控制。

Gait Optimization Research on RoboCup3D Simulation

(1. College of Computer and Information, Hohai University, Nanjing 210098, China;

2. School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213002, China)

Received:2017-09-21 Online:2018-04-03 Published:2018-04-03

摘要/Abstract

摘要： 在RoboCup3D比赛中，拥有一个快速灵活、稳定的步态模式是赢得机器人足球比赛的关键之一。为了获得这样的步态模式，提出一种双足机器人垂直质心高度可变的机器学习训练方法。首先，通过规划双足机器人垂直质心高度的轨迹、利用倒立摆模型和数值化方法控制零力矩点，实现双足机器人的类人行走。然后，采用自适应协方差矩阵进化算法对步态参数优化，为了获得快速稳定的步行，采用累积分层的学习方法在之前优化的基础上进一步优化。最后，采用蜂拥编队壁障算法验证多机器人环境下优化步态的稳定性、灵活性。实验和竞赛结果均表明本文提出算法的有效性。

关键词: 双足机器人, 步态优化, 倒立摆模型, 进化算法, 机器人世界杯

Abstract: In the RoboCup3D competition, a flexible and stable gait pattern is one of the key for the humanoid robot to win the match, to achieve such walk gait, a machine learning method of optimizing the vertical Center of Mass(Com) trajectory is presented. Firstly, to generate bipedal walk slowly and unsteadily, the vertical Com trajectory is planed by multiple polynomial, the inverted pendulum model(IPM) and a numerical method are utilized to control the Zero Moment Point(ZMP). Secondly, to get a fast and stable bipedal walk, a overlapping layered learning method is proposed to optimize the walking parameters which is based on Covariance Matrix Adaptation Evolution Strategy(CMA-ES). Finally, flocking control is applied to verify the flexibilty of the optimized gait in multi-robot environment. The experimental and competition results show that the proposed method is effective.

Key words: humaniod robot, gait optimization, IPM, evolutionary algorithm, RoboCup

中图分类号:

TP242.6

何荣义1,李春光2. RoboCup3D仿真机器人步态优化研究[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.03.004.

HE Rong-yi1, LI Chun-guang2. Gait Optimization Research on RoboCup3D Simulation[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.03.004.

参考文献

［1］ Graf C, Rfer T. A center of mass observing 3D-LIPM gait for the RoboCup standard platform league humanoid［C］// Springer Berlin Heidelberg: Robot Soccer World Cup. 2011:101-112.
［2］ Kuo A D, Donelan J M, Ruina A. Energetic consequences of walking like an inverted pendulum: Step-to-step transitions［J］. Exercise and Sport Sciences Reviews, 2005,33(2):88-97.
［3］ Guo Fayong, Zhao Jianghai, Mei Tao, et al. A modified gait generator for humanoid robots based on height compensation of center of mass［C］// 2014 IEEE International Conference on Robotics and Biomimetics(ROBIO). 2014:1278-1283.
［4］ Hong Y D, Lee K B. Stable walking of humanoid robots using vertical center of mass and foot motions by an evolutionary optimized central pattern generator［J］. International Journal of Advanced Robotic System, 2016,13(1):27.
［5］ Macalpine P, Barrett S, Urieli D, et al. Design and optimization of an omnidirectional humanoid walk: A winning approach at the RoboCup 2011 3D simulation competition［C］// Proceedings of the 26th AAAI Conference on Artificial Intelligence. 2012:1047-1053.
［6］ Hansen N. The CMA Evolution Strategy: A Tutorial［EB/OL］. http://www2.fiit.stuba.sk/~kvasnicka/Seminar_of_AI/Hansen_CMA_tutorial.pdf, 2009-01-18.
［7］ Shafii N, Aslani S, Nezami O M, et al. Evolution of biped walking using truncated fourier series and particle swarm optimization［M］// RoboCup 2009: Robot Soccer World Cup XIII. 2009:344-354.
［8］ Kajita S, Nagasaki T, Yokoi K, et al. Running pattern generation for a humanoid robot［C］// Proceedings of 2002 IEEE International Conference on Robotics and Automation. 2002:2755-2761.
［9］ Kagami S, Kitagawa T, Nishiwaki K, et al. A fast dynamically equilibrated walking trajectory generation method of humanoid robot［J］. Autonomous Robots, 2002,12(1):71-82.
［10］MacAlpine P, Depinet M, Stone P. UT Austin Villa 2014: RoboCup 3D simulation league champion via overlapping layered learning［C］// Proceedings of the 29th AAAI Conference Intelligence(AAAI-15). 2015:2842-2848.
［11］Shafii N, Lau N, Reis L P. Learning to walk fast: Optimized hip height movement for simulated and real humanoid robots［J］. Journal of Intelligent & Robotic Systems, 2015,80(3-4):555-571.
［12］Erbatur K, Kurt O. Natural ZMP trajectories for biped robot reference generation［J］. IEEE Transactions on Industrial Electronics, 2009,56(3):835-845.
［13］李春光. 仿人机器人运动规划与蜂拥控制研究［D］. 无锡:江南大学, 2015.
［14］蔡朝宏,江红. 一种双足步行的累积分层优化方法［J］. 小型微型计算机系统, 2013,34(5):1132-1136.
［15］Xu Yuan, Vatankhah H. Simspark: An open source robot simulator developed by the RoboCup community［C］// Proceedings of the 17th Annual RoboCup International Symposium. 2013:632-639.
［16］Farchy A, Barrett S, MacAlpine P, et al. Humanoid robots learning to walk faster: From the real world to simulation and back［C］// Proceedings of 2013 International Conference on Autonomous Agents and Multi-agent Systems. 2013:39-46.
［17］Li Chunguang, Tao Chongben, Liu Guodong, et al. Quantized flocking control for second-order multiple agents with obstacle avoidance［J］. Advances in Mechanical Engineering, 2016,8(1).

[1]	鄂翔南1，刘泽平2，张子晔3. 基于差分进化算法的面目标瞄准点寻优[J]. 计算机与现代化, 2019, 0(12): 27-.
[2]	陈泯融，黄广敬. 基于分解的多目标花朵授粉算法[J]. 计算机与现代化, 2019, 0(07): 1-.
[3]	袁雯，刘惠义. 基于深度Q网络的仿人机器人步态优化[J]. 计算机与现代化, 2019, 0(04): 47-.
[4]	张春燕. 改进多目标进化算法求解柔性作业车间调度问题[J]. 计算机与现代化, 2017, 0(9): 79-84.
[5]	杨争光1,2,范良忠2. 基于MEC-BP神经网络在水产养殖水质预测中的应用[J]. 计算机与现代化, 2015, 0(6): 32-36.
[6]	姜凯，苑金海. 融合差分进化和SOM的组合文本聚类算法[J]. 计算机与现代化, 2015, 0(5): 13-16+20.
[7]	王晓萍1，孟坤2. 基于约束处理和平滑技术的改进的进化算法[J]. 计算机与现代化, 2014, 0(9): 1-5.
[8]	殷昭宁;孙靖. 三种基于偏好的区间多目标进化算法及应用[J]. 计算机与现代化, 2012, 1(11): 43-46.
[9]	丛婷婷;祝永志. 并行差分进化算法[J]. 计算机与现代化, 2011, 1(1): 49-3.

RoboCup3D仿真机器人步态优化研究

Gait Optimization Research on RoboCup3D Simulation

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价