Systematic Derivation of Behaviour Characterisations in Evolutionary Robotics

被引:13
作者
Gomes, Jorge [1 ,2 ]
Mariano, Pedro [2 ]
Christensen, Anders Lyhne [1 ,3 ]
机构
[1] Inst Telecomunicacoes, Lisbon, Portugal
[2] Univ Lisbon, Fac Ciencias, LabMAg, Lisbon, Portugal
[3] Inst Univ Lisboa ISCTE IUL, Lisbon, Portugal
来源
ALIFE 2014: THE FOURTEENTH INTERNATIONAL CONFERENCE ON THE SYNTHESIS AND SIMULATION OF LIVING SYSTEMS | 2014年
关键词
D O I
10.7551/978-0-262-32621-6-ch036
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Evolutionary techniques driven by behavioural diversity, such as novelty search, have shown significant potential in evolutionary robotics. These techniques rely on priorly specified behaviour characterisations to estimate the similarity between individuals. Characterisations are typically defined in an ad hoc manner based on the experimenter's intuition and knowledge about the task. Alternatively, generic characterisations based on the sensor-effector values of the agents are used. In this paper, we propose a novel approach that allows for systematic derivation of behaviour characterisations for evolutionary robotics, based on a formal description of the agents and their environment. Systematically derived behaviour characterisations (SDBCs) go beyond generic characterisations in that they can contain task-specific features related to the internal state of the agents, environmental features, and relations between them. We evaluate SDBCs with novelty search in three simulated collective robotics tasks. Our results show that SDBCs yield a performance comparable to the task-specific characterisations, in terms of both solution quality and behaviour space exploration.
引用
收藏
页码:212 / 219
页数:8
相关论文
共 23 条
[1]  
[Anonymous], 2010, EVOLUTIONARY COMPUTA
[2]   USING MUTUAL INFORMATION FOR SELECTING FEATURES IN SUPERVISED NEURAL-NET LEARNING [J].
BATTITI, R .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (04) :537-550
[3]  
Cuccu G, 2011, LECT NOTES COMPUT SC, V6624, P234, DOI 10.1007/978-3-642-20525-5_24
[4]  
d'Inverno M., 2004, SPRI SER AG TECHNOL, V2nd
[5]   A fast and elitist multiobjective genetic algorithm: NSGA-II [J].
Deb, K ;
Pratap, A ;
Agarwal, S ;
Meyarivan, T .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (02) :182-197
[6]  
Doncieux S, 2013, 2013 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P1427
[7]  
Goldberg D. E., 1987, Genetic Algorithms and their Applications: Proceedings of the Second International Conference on Genetic Algorithms, P41
[8]  
Gomes J, 2014, AAMAS'14: PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS, P1149
[9]  
Gomes J, 2013, GECCO'13: PROCEEDINGS OF THE 2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, P199
[10]   Evolution of swarm robotics systems with novelty search [J].
Gomes, Jorge ;
Urbano, Paulo ;
Christensen, Anders Lyhne .
SWARM INTELLIGENCE, 2013, 7 (2-3) :115-144