Flocking in Stationary and Non-stationary Environments: A Novel Communication Strategy for Heading Alignment

被引:0
|
作者
Ferrante, Eliseo [1 ]
Turgut, Ali Emre [1 ]
Mathews, Nithin [1 ]
Birattari, Mauro [1 ]
Dorigo, Marco [1 ]
机构
[1] Univ Libre Bruxelles, CoDE, IRIDIA, Brussels, Belgium
来源
PARALLEL PROBLEM SOLVING FROM NATURE-PPSN XI, PT II | 2010年 / 6239卷
关键词
MINORITY;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We propose a novel communication strategy inspired by explicit signaling mechanisms seen in vertebrates, in order to improve performance of self-organized flocking for a swarm of mobile robots. The communication strategy is used to make the robots match each other's headings. The task of the robots is to coordinately move towards a common goal direction, which might stay fixed or change over time. We perform simulation-based experiments in which we evaluate the accuracy of flocking with respect to a given goal direction. In our settings, only some of the robots are informed about the goal direction. Experiments are conducted in stationary and non-stationary environments. In the stationary environment, the goal direction and the informed robots do not change during the experiment. In the non-stationary environment, the goal direction and the informed robots are changed over time. In both environments, the proposed strategy scales well with respect to the swarm size and is robust with respect to noise.
引用
收藏
页码:331 / 340
页数:10
相关论文
共 50 条
  • [41] Stochastic Bandits with Graph Feedback in Non-Stationary Environments
    Lu, Shiyin
    Hu, Yao
    Zhang, Lijun
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 8758 - 8766
  • [42] Minority games and distributed coordination in non-stationary environments
    Galstyan, A
    Lerman, K
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 2610 - 2614
  • [43] A robust incremental learning method for non-stationary environments
    Martinez-Rego, David
    Perez-Sanchez, Beatriz
    Fontenla-Romero, Oscar
    Alonso-Betanzos, Amparo
    NEUROCOMPUTING, 2011, 74 (11) : 1800 - 1808
  • [44] Learning Optimal Behavior in Environments with Non-stationary Observations
    Boone, Ilio
    Rens, Gavin
    ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 3, 2022, : 729 - 736
  • [45] A heterogeneous online learning ensemble for non-stationary environments
    Idrees, Mobin M.
    Minku, Leandro L.
    Stahl, Frederic
    Badii, Atta
    KNOWLEDGE-BASED SYSTEMS, 2020, 188
  • [46] Reinforcement learning in episodic non-stationary Markovian environments
    Choi, SPM
    Zhang, NL
    Yeung, DY
    IC-AI '04 & MLMTA'04 , VOL 1 AND 2, PROCEEDINGS, 2004, : 752 - 758
  • [47] Sub-structural niching in non-stationary environments
    Sastry, T
    Abbass, LA
    Goldberg, T
    AI 2004: ADVANCES IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2004, 3339 : 873 - 885
  • [48] An Online Algorithm for Computation Offloading in Non-Stationary Environments
    Rahman, Aniq Ur
    Ghatak, Gourab
    De Domenico, Antonio
    IEEE COMMUNICATIONS LETTERS, 2020, 24 (10) : 2167 - 2171
  • [49] Adaptive deep reinforcement learning for non-stationary environments
    Jin ZHU
    Yutong WEI
    Yu KANG
    Xiaofeng JIANG
    Geir E.DULLERUD
    Science China(Information Sciences), 2022, 65 (10) : 225 - 241
  • [50] Recursive Adaptation of Stepsize Parameter for Non-stationary Environments
    Noda, Itsuki
    PRINCIPLES OF PRACTICE IN MULTI-AGENT SYSTEMS, 2009, 5925 : 525 - 533