Generating Collective Motion Behaviour Libraries Using Developmental Evolution
Authors: 
Md Khan, Kathryn Kasmarik, Michael Barlow, Shadi Abpeikar, Huanneng Qiu, Essam Debie, Matt GarrattAuthors Info & Claims
Md Khan, Kathryn Kasmarik, Michael Barlow, Shadi Abpeikar, Huanneng Qiu, Essam Debie, Matt GarrattAuthors Info & ClaimsPages 441 - 452
Abstract
This paper presents an evolutionary framework for generating diverse libraries of collective motion behaviours. It builds upon recent advancements in machine recognition of collective motion and the transformation of random motions into structured collective behaviours. The paper describes the design of the framework, including the use of a fitness function and diversity metrics specifically tailored for this purpose. The proposed framework generates diverse behaviours with distinct collective motion characteristics. Analysing the relationship between genotypic and behavioural diversity, we observed that greater diversity emerges after a moderate number of evolutionary generations. Our findings highlight the effectiveness of task non-specific fitness functions in distinguishing structured collective behaviours in an evolutionary setting.
References
[1]
Abpeikar, S., Kasmarik, K., Garratt, M., Hunjet, R., Khan, M.M., Qiu, H.: Automatic collective motion tuning using actor-critic deep reinforcement learning. Swarm Evol. Comput. 101085 (2022)
[2]
Barlow, M., Lakshika, E.: What cost teamwork: quantifying situational awareness and computational requirements in a proto-team via multi-objective evolution. In: 2016 IEEE Congress on Evolutionary Computation (CEC) (2016)
[3]
Eshelman, L., Schaffer, J.: Real-coded genetic algorithms and interval-schemata. In: Foundations of Genetic Algorithms, vol. 2, p. 187–202. Elsevier (1993)
[4]
Ferrante E, Turgut A, Stranieri A, Pinciroli C, Birattari M, and Dorigo M A self-adaptive communication strategy for flocking in stationary and non-stationary environments Natural Comput. 2014 13 2 225-245
[5]
Gomes J, Urbano P, and Christensen A Evolution of swarm robotics systems with novelty search Swarm Intell. 2013 7 2–3 115-144
[6]
Hamann, H.: Evolution of collective behaviours by minimizing surprise. In: ALIFE2014 (2014)
[7]
Harik, G.: Finding multimodal solutions using restricted tournament selection. In: ICGA (1995)
[8]
Harvey J, Merrick KE, and Abbass HA Assessing human judgment of computationally generated swarming behavior Front. Robot. AI 2018 5 13
[9]
Harvey J, Merrick K, and Abbass H Tan Y, Shi Y, and Niu B Quantifying swarming behaviour Advances in Swarm Intelligence 2016 Cham Springer 119-130
[10]
Khan M, Kasmarik K, and Barlow M Autonomous detection of collective behaviours in swarms Swarm Evol. Comput. 2020 57 100715
[11]
Merrick K and Maher M Motivated Reinforcement Learning: Curious Characters for Multiuser Games 2009 Berlin Springer
[12]
Reynolds, C.: Flocks, herds and schools: a distributed behavioral model. In: Computer Graphics (SIGGRAPH 1987) Conference Proceedings, vol. 21, no. 4, pp. 25–34 (1987)
[13]
Shafi K, Merrick KE, and Debie E Bui LT, Ong YS, Hoai NX, Ishibuchi H, and Suganthan PN Evolution of intrinsic motives in multi-agent simulations Simulated Evolution and Learning 2012 Heidelberg Springer 198-207
[14]
Vesanto, J., Himberg, J., Alhoniemi, E., Parhankangas, J.: Self-organizing map in matlab: the SOM toolbox. In: Proceedings of the Matlab DSP Conference (1999)
Recommendations
Differential evolution powered by collective information
Differential evolution (DE) algorithms have demonstrated excellence performance in dealing with global optimization problems. In DE, mutation is the sole process providing new components to form potential candidates, and it does so by combining various ...
Constrained differential evolution using generalized opposition-based learning
Differential evolution (DE) is a well-known optimization approach to deal with nonlinear and complex optimization problems. However, many real-world optimization problems are constrained problems that involve equality and inequality constraints. DE with ...
A model for analysing the collective dynamic behaviour and characterising the exploitation of population-based algorithms
Several previous studies have focused on modelling and analysing the collective dynamic behaviour of population-based algorithms. However, an empirical approach for identifying and characterising such a behaviour is surprisingly lacking. In this paper, ...
Comments
Information & Contributors
Information
Published In
Nov 2023
508 pages
ISBN:978-981-99-8390-2
DOI:10.1007/978-981-99-8391-9
- Editors:
- Tongliang Liu,
- Geoff Webb,
- Lin Yue,
- Dadong Wang
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 28 November 2023
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 15 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in