Real-World Evolution of Robot Morphologies: A Proof of Concept

被引:42
作者
Jelisavcic, Milan [1 ]
de Carlo, Matteo [1 ]
Hupkes, Elte [2 ]
Eustratiadis, Panagiotis [1 ]
Orlowski, Jakub [3 ]
Haasdijk, Evert [1 ]
Auerbach, Joshua E. [4 ]
Eiben, A. E. [1 ]
机构
[1] Vrije Univ Amsterdam, Amsterdam, Netherlands
[2] Univ Amsterdam, Amsterdam, Netherlands
[3] Univ Warsaw, Warsaw, Poland
[4] Champlain Coll, Burlington, VT USA
关键词
Evolutionary robotics; embodied evolution; modular robots; artificial life; DESIGN;
D O I
10.1162/ARTL_a_00231
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Evolutionary robotics using real hardware has been almost exclusively restricted to evolving robot controllers, but the technology for evolvable morphologies is advancing quickly. We discuss a proof-of-concept study to demonstrate real robots that can reproduce. Following a general system plan, we implement a robotic habitat that contains all system components in the simplest possible form. We create an initial population of two robots and run a complete life cycle, resulting in a new robot, parented by the first two. Even though the individual steps are simplified to the maximum, the whole system validates the underlying concepts and provides a generic workflow for the creation of more complex incarnations. This hands-on experience provides insights and helps us elaborate on interesting research directions for future development.
引用
收藏
页码:206 / 235
页数:30
相关论文
共 47 条
  • [31] Kuehn T, 2012, ARTIF LIFE, V13, P372
  • [32] Levi P., 2010, Symbiotic Multi-Robot Organisms: Reliability, Adaptability, Evolution
  • [33] Automatic design and manufacture of robotic lifeforms
    Lipson, H
    Pollack, JB
    [J]. NATURE, 2000, 406 (6799) : 974 - 978
  • [34] Nolfi S., 2000, Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-organizing Machines
  • [35] Rieffel J, 2010, LECT NOTES COMPUT SC, V6274, P372, DOI 10.1007/978-3-642-15323-5_32
  • [36] Simultaneous versus incremental learning of multiple skills by modular robots
    Rossi, C.
    Eiben, A. E.
    [J]. EVOLUTIONARY INTELLIGENCE, 2014, 7 (02) : 119 - 131
  • [37] Learning Fast Quadruped Robot Gaits with the RL PoWER Spline Parameterization
    Shen, Haocheng
    Yosinski, Jason
    Kormushev, Petar
    Caldwell, Darwin G.
    Lipson, Hod
    [J]. CYBERNETICS AND INFORMATION TECHNOLOGIES, 2012, 12 (03) : 66 - 75
  • [38] Trianni V, 2008, STUD COMPUT INTELL, V108, P3
  • [39] Upton E., 2014, Raspberry Pi user guide
  • [40] Vargas PA, 2014, INTEL ROBOT AUTON AG, P1