模块化机器人的模块形态特性
|
摘要
针对目前尚无一种通用的方法对模块形态与模块化机器人的性能关系进行分析研究,以EMERGE模块形态为目标对象,基于进化设计的思想,提出一种模块形态的评估方法。首先,依据模块可用的连接面数量及其相对位置对模块形态进行分类分析。然后采用结构化的进化设计策略,以平面的移动任务为算例,在机器人仿真平台中分别对由不同种类形态的模块组建的机器人进化,得到每种模块形态下性能最优的机器人,并比较各自的性能。最后,对不同种类的最优性能的仿真机器人进行实体机器人验证。结果表明该评估方法可有效提高设计高性能模块化机器人的效率,仿真和实体机器人试验验证了方法的有效性。
Module morphology refers to all the factors related to the physical realization of the modules.There has been no a general approach to analyze the relationship between module morphology and the performance of modular robots.In this paper,based on the Easy Modular Embodied Robot Generation(EMERGE),an evaluation approach of the module morphology is proposed based on evolutionary design idea.First,the module morphology is classified according to the available number of connection faces and their relative positions.Then,using the structured evolutionary design strategy,modular robots composed of different module morphologies are evolved for the locomotion task in a simulation robotic platform,in order to obtain the best morphologies of modular robot and compare their performance.Finally,the simulated robots are transferred to the physical robots to verify the result.The simulation and experimental results show that the proposed approach can help to improve efficiency of designing robotic morphologies.
Module morphology refers to all the factors related to the physical realization of the modules.There has been no a general approach to analyze the relationship between module morphology and the performance of modular robots.In this paper,based on the Easy Modular Embodied Robot Generation(EMERGE),an evaluation approach of the module morphology is proposed based on evolutionary design idea.First,the module morphology is classified according to the available number of connection faces and their relative positions.Then,using the structured evolutionary design strategy,modular robots composed of different module morphologies are evolved for the locomotion task in a simulation robotic platform,in order to obtain the best morphologies of modular robot and compare their performance.Finally,the simulated robots are transferred to the physical robots to verify the result.The simulation and experimental results show that the proposed approach can help to improve efficiency of designing robotic morphologies.
引文
[1]Stoy K,Brandt D,Christensen D J,et al.Selfreconfigurable Robots:an Introduction[M].Cambridge:MIT Press,2010:2-4.
[2]Pfeifer R,Bongard J.How the Body Shapes the Way We Think:a New View of Intelligence[M].Cambridge:MIT Press,2006:13-25.
[3]Paul C.Morphological computation:a basis for the analysis of morphology and control requirements[J].Robotics and Autonomous Systems,2006,54(8):619-630.
[4]Stoy K,Brandt D.Efficient enumeration of modular robot configurations and shapes[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS),Tokyo,Japan,2013:4296-4301.
[5]Murata S,Yoshida E,Kamimura A,et al.MTRAN:self-reconfigurable modular robotic system[J].IEEE/ASME Transactions on Mechatronics,2002,7(4):431-441.
[6]Shen W M,Krivokon M,Chiu H,et al.Multimode locomotion via SuperBot reconfigurable robots[J].Autonomous Robots,2006,20(2):165-177.
[7]Gilpin K,Kotay K,Rus D,et al.Miche:modular shape formation by self-disassembly[J].The International Journal of Robotics Research,2008,27(3/4):345-372.
[8]赵杰,唐术锋,朱延河,等.基于万向式关节的模块化自重构机器人[J].机器人,2010,32(5):608-613.Zhao Jie,Tang Shu-feng,Zhu Yan-he,et al.A modular self-reconfigurable robot based on universal joint[J].Robot,2010,32(5):608-613.
[9]Zhao J,Wei Y,Fan J,et al.New type reconfigurable modular robot design and intelligent control method research[C]∥The 6th World Conference on Intelligent Control and Automation,Dalian,China,2006:8907-8911.
[10]Guan Y,Jiang L,Zhang X.Mechanical design and basic analysis of a modular robot with special climbing and manipulation functions[C]∥IEEE International Conference on Robotics and Biomimetics,Sanya,China,2007:502-507.
[11]李航,李敏强,寇纪淞.基于搜索空间信息的新型遗传算法[J].计算机工程,2007,35(9):22-24,65.Li Hang,Li Min-qiang,Kou Ji-song.Improved genetic algorithm based on information searching space[J].Computer Engineering,2007,35(9):22-24,65.
[12]Sims K.Evolving virtual creatures[C]∥Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques,Orlando,USA,1994:15-22.
[13]Komosinski M.The Framsticks system:versatile simulator of 3Dagents and their evolution[J].Kybernetes,2003,32(1/2):156-173.
[14]Mazzapioda M,Cangelosi A,Nolfi S.Evolving morphology and control:a distributed approach[C]∥IEEE Conference on Evolutionary Computation,Trondheim,Norway,2009:2217-2224.
[15]Pollack J B,Lipson H.The GOLEM project:evolving hardware bodies and brains[C]∥The Second NASA/DoD Workshop on Evolvable Hardware,Palo Alto,CA,USA,2000:37-42.
[16]Marbach D,Ijspeert A J.Co-evolution of configuration and control for homogenous modular robots[C]∥Proceedings of the 8th Conference on Intelligent Autonomous Systems(IAS8),Marrakech,Morocco,2004:712-719.
[17]Lund H H.Co-evolving Control and Morphology with LEGO Robots[M].Hara Fumio,Pfeifer Rolf.Morpho-functional Machines:the New Species,Tokyo:Springer,2003:59-79.
[18]Faí1a A,Bellas F,López-Pe1a F,et al.EDHMoR:Evolutionary designer of heterogeneous modular robots[J].Engineering Applications of Artificial Intelligence,2013,26(10):2408-2423.
[19]Freese M,Singh S,Ozaki F,et al.Virtual robot experimentation platform V-REP:A versatile 3drobot simulator[C]∥International Conference on Simulation,Modeling,and Programming for Autonomous Robots,Berlin:Germany,2010:51-62.
[20]Bongard J C.The impact of jointly evolving robot morphology and control on adaptation rate[C]∥Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation,ACM,2009:1769-1770.
[21]Veenstra F,Faina A,Risi S,et al.Evolution and morphogenesis of simulated modular robots:a comparison between a direct and generative encoding[C]∥European Conference on the Applications of Evolutionary Computation,Springer,Cham,2017:870-885.
[22]崔馨丹.模块化自重构机器人仿生运动规划与控制[D].哈尔滨:哈尔滨工业大学机器人技术与系统国家重点实验室,2013.Cui Xin-dan.Biomimetic motion plan and control of modular self-reconfigurable robot[D].Harbin:State Key Laboratory of Robotics Technology and Systems,Harbin Institute of Technology,2013.
[23]蒋湘军,魏武.基于形态学的蛇形机器人运动步态算法研究[J].计算机工程与设计,2011,32(9):3140-3143.Jiang Xiang-jun, Wei Wu. Algorithm study of snake-like robot′s gaits based on morphology[J].Computer Engineering and Design,2011,32(9):3140-3143.
[24]陈海英,郭巧.进化机器人[J].机器人,2003,24(1):92-96.Chen Hai-ying,Guo Qiao.Evolutionary robots[J].Robot,2003,24(1):92-96.
[25]王晓露.模块化机器人协调运动规划与运动能力进化研究[D].哈尔滨:哈尔滨工业大学机器人技术与系统国家重点实验室,2016.Wang Xiao-lu.Research on coordinated locomotion planning and evolution for modular self-reconfigurable robots[D].Harbin:State Key Laboratory of Robotics Technology and Systems,Harbin Institute of Technology,2016.
[26]张宇山.进化算法的收敛性与时间复杂度分析的若干研究[D].广州:华南理工大学数学学院,2013.Zhang Yu-shan.Some studies on the convergence and time complexity analysis of evolutionary algorithms[D].Guangzhou:School of Mathematics,South China University of Technology,2013.
[2]Pfeifer R,Bongard J.How the Body Shapes the Way We Think:a New View of Intelligence[M].Cambridge:MIT Press,2006:13-25.
[3]Paul C.Morphological computation:a basis for the analysis of morphology and control requirements[J].Robotics and Autonomous Systems,2006,54(8):619-630.
[4]Stoy K,Brandt D.Efficient enumeration of modular robot configurations and shapes[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS),Tokyo,Japan,2013:4296-4301.
[5]Murata S,Yoshida E,Kamimura A,et al.MTRAN:self-reconfigurable modular robotic system[J].IEEE/ASME Transactions on Mechatronics,2002,7(4):431-441.
[6]Shen W M,Krivokon M,Chiu H,et al.Multimode locomotion via SuperBot reconfigurable robots[J].Autonomous Robots,2006,20(2):165-177.
[7]Gilpin K,Kotay K,Rus D,et al.Miche:modular shape formation by self-disassembly[J].The International Journal of Robotics Research,2008,27(3/4):345-372.
[8]赵杰,唐术锋,朱延河,等.基于万向式关节的模块化自重构机器人[J].机器人,2010,32(5):608-613.Zhao Jie,Tang Shu-feng,Zhu Yan-he,et al.A modular self-reconfigurable robot based on universal joint[J].Robot,2010,32(5):608-613.
[9]Zhao J,Wei Y,Fan J,et al.New type reconfigurable modular robot design and intelligent control method research[C]∥The 6th World Conference on Intelligent Control and Automation,Dalian,China,2006:8907-8911.
[10]Guan Y,Jiang L,Zhang X.Mechanical design and basic analysis of a modular robot with special climbing and manipulation functions[C]∥IEEE International Conference on Robotics and Biomimetics,Sanya,China,2007:502-507.
[11]李航,李敏强,寇纪淞.基于搜索空间信息的新型遗传算法[J].计算机工程,2007,35(9):22-24,65.Li Hang,Li Min-qiang,Kou Ji-song.Improved genetic algorithm based on information searching space[J].Computer Engineering,2007,35(9):22-24,65.
[12]Sims K.Evolving virtual creatures[C]∥Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques,Orlando,USA,1994:15-22.
[13]Komosinski M.The Framsticks system:versatile simulator of 3Dagents and their evolution[J].Kybernetes,2003,32(1/2):156-173.
[14]Mazzapioda M,Cangelosi A,Nolfi S.Evolving morphology and control:a distributed approach[C]∥IEEE Conference on Evolutionary Computation,Trondheim,Norway,2009:2217-2224.
[15]Pollack J B,Lipson H.The GOLEM project:evolving hardware bodies and brains[C]∥The Second NASA/DoD Workshop on Evolvable Hardware,Palo Alto,CA,USA,2000:37-42.
[16]Marbach D,Ijspeert A J.Co-evolution of configuration and control for homogenous modular robots[C]∥Proceedings of the 8th Conference on Intelligent Autonomous Systems(IAS8),Marrakech,Morocco,2004:712-719.
[17]Lund H H.Co-evolving Control and Morphology with LEGO Robots[M].Hara Fumio,Pfeifer Rolf.Morpho-functional Machines:the New Species,Tokyo:Springer,2003:59-79.
[18]Faí1a A,Bellas F,López-Pe1a F,et al.EDHMoR:Evolutionary designer of heterogeneous modular robots[J].Engineering Applications of Artificial Intelligence,2013,26(10):2408-2423.
[19]Freese M,Singh S,Ozaki F,et al.Virtual robot experimentation platform V-REP:A versatile 3drobot simulator[C]∥International Conference on Simulation,Modeling,and Programming for Autonomous Robots,Berlin:Germany,2010:51-62.
[20]Bongard J C.The impact of jointly evolving robot morphology and control on adaptation rate[C]∥Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation,ACM,2009:1769-1770.
[21]Veenstra F,Faina A,Risi S,et al.Evolution and morphogenesis of simulated modular robots:a comparison between a direct and generative encoding[C]∥European Conference on the Applications of Evolutionary Computation,Springer,Cham,2017:870-885.
[22]崔馨丹.模块化自重构机器人仿生运动规划与控制[D].哈尔滨:哈尔滨工业大学机器人技术与系统国家重点实验室,2013.Cui Xin-dan.Biomimetic motion plan and control of modular self-reconfigurable robot[D].Harbin:State Key Laboratory of Robotics Technology and Systems,Harbin Institute of Technology,2013.
[23]蒋湘军,魏武.基于形态学的蛇形机器人运动步态算法研究[J].计算机工程与设计,2011,32(9):3140-3143.Jiang Xiang-jun, Wei Wu. Algorithm study of snake-like robot′s gaits based on morphology[J].Computer Engineering and Design,2011,32(9):3140-3143.
[24]陈海英,郭巧.进化机器人[J].机器人,2003,24(1):92-96.Chen Hai-ying,Guo Qiao.Evolutionary robots[J].Robot,2003,24(1):92-96.
[25]王晓露.模块化机器人协调运动规划与运动能力进化研究[D].哈尔滨:哈尔滨工业大学机器人技术与系统国家重点实验室,2016.Wang Xiao-lu.Research on coordinated locomotion planning and evolution for modular self-reconfigurable robots[D].Harbin:State Key Laboratory of Robotics Technology and Systems,Harbin Institute of Technology,2016.
[26]张宇山.进化算法的收敛性与时间复杂度分析的若干研究[D].广州:华南理工大学数学学院,2013.Zhang Yu-shan.Some studies on the convergence and time complexity analysis of evolutionary algorithms[D].Guangzhou:School of Mathematics,South China University of Technology,2013.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |