Evolving Self-Assembly in Autonomous Homogeneous Robots: Experiments with Two Physical Robots

被引:34
作者
Ampatzis, Christos [1 ]
Tuci, Elio [2 ]
Trianni, Vito [2 ]
Christensen, Anders Lyhne [3 ]
Dorigo, Marco [4 ]
机构
[1] European Space Agcy, Adv Concepts Team, Estec, NL-2200 AG Noordwijk, Netherlands
[2] ISTC CNR, I-00185 Rome, Italy
[3] DCTI ISCTE, P-1649026 Lisbon, Portugal
[4] Univ Libre Bruxelles, CoDE IRIDIA, B-1050 Brussels, Belgium
关键词
Self-assembly; role allocation; neural network; artificial evolution; evolutionary robotics; COORDINATED MOTION; COOPERATION;
D O I
10.1162/artl.2009.Ampatzis.013
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This research work illustrates an approach to the design of controllers for self-assembling robots in which the self-assembly is initiated and regulated by perceptual cues that are brought forth by the physical robots through their dynamic interactions. More specifically, we present a homogeneous control system that can achieve assembly between two modules (two fully autonomous robots) of a mobile self-reconfigurable system without a priori introduced behavioral or morphological heterogeneities. The controllers are dynamic neural networks evolved in simulation that directly control all the actuators of the two robots. The neurocontrollers cause the dynamic specialization of the robots by allocating roles between them based solely on their interaction. We show that the best evolved controller proves to be successful when tested on a real hardware platform, the swarm-bot. The performance achieved is similar to the one achieved by existing modular or behavior-based approaches, also due to the effect of an emergent recovery mechanism that was neither explicitly rewarded by the fitness function, nor observed during the evolutionary simulation. Our results suggest that direct access to the orientations or intentions of the other agents is not a necessary condition for robot coordination: Our robots coordinate without direct or explicit communication, contrary to what is assumed by most research work in collective robotics. This work also contributes to strengthening the evidence that evolutionary robotics is a design methodology that can tackle real-world tasks demanding fine sensory-motor coordination.
引用
收藏
页码:465 / 484
页数:20
相关论文
共 44 条
  • [1] Self-assemblages in insect societies
    Anderson, C
    Theraulaz, G
    Deneubourg, JL
    [J]. INSECTES SOCIAUX, 2002, 49 (02) : 99 - 110
  • [2] [Anonymous], 1988, PROC IEEE INT WORKSH
  • [3] [Anonymous], 1999, Swarm Intelligence
  • [4] Active self-assembly
    Arbuckle, D
    Requicha, AAG
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS, 2004, : 896 - 901
  • [5] Self-organized coordinated motion in groups of physically connected robots
    Baldassarre, Gianluca
    Trianni, Vito
    Bonani, Michael
    Mondada, Francesco
    Dorigo, Marco
    Nolfi, Stefano
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2007, 37 (01): : 224 - 239
  • [6] Parameter space structure of continuous-time recurrent neural networks
    Beer, Randall D.
    [J]. NEURAL COMPUTATION, 2006, 18 (12) : 3009 - 3051
  • [7] Beer Randall D., 1992, Adaptive Behavior, V1, P91, DOI 10.1177/105971239200100105
  • [8] The dynamics of active categorical perception in an evolved model agent
    Beer, RD
    [J]. ADAPTIVE BEHAVIOR, 2003, 11 (04) : 209 - 243
  • [9] Millibot trains for enhanced mobility
    Brown, HB
    Vande Weghe, JM
    Bererton, CA
    Khosla, PK
    [J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2002, 7 (04) : 452 - 461
  • [10] CONRO: Towards deployable robots with inter-robots metamorphic capabilities
    Castano, A
    Shen, WM
    Will, P
    [J]. AUTONOMOUS ROBOTS, 2000, 8 (03) : 309 - 324