Designing emergent cooperation: a pursuit–evasion game case study

Nitschke, Geoff

doi:10.1007/s10015-005-0349-5

Cited by 7 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, prey capture was made more difficult via giving the prey an advantage of greater speed. Nitschke [74] elucidated that at least two predators were required to accomplish this task, and that predators in a team adopting complementary behavioral specializations yielded the benefit of increasing the time for which a prey was captured. The beneficial forms of predator behavioral specialization, and collective prey capture behaviors were not known a priori, and were thus evolved by CCGA, MESP or CONE.…”

Section: Methodsmentioning

confidence: 99%

“…This article's case study was an ER task that simulated robot teams (predators) that had to immobilize (capture) one or two other robots (prey) in a bounded environment. This pursuitevasion task required different predators in a team to assume complementary behaviorally specializations in order for the team to achieve an optimal or near optimal task performance [74]. A thorough analysis of the pursuit-evasion task was conducted to support this.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolving team behaviors with specialization

Nitschke

Eiben

Schut

2012

Genet Program Evolvable Mach

View full text Add to dashboard Cite

This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evolving team behaviors with specialization

Nitschke

Eiben

Schut

2012

Genet Program Evolvable Mach

View full text Add to dashboard Cite

show abstract

“…Figure 4 (left and right hand side) illustrate the two versions of the role switcher prey-capture behavior, occurring over w simulation time steps. The role switcher behavior has been observed in related research [7], and is thus not elaborated upon here.…”

Section: Esp: Role-switcher Prey Capture Behaviormentioning

confidence: 88%

“…A recurrent neural network was selected as the predator controller in order to emulate short term memory [3]. A hidden layer of 6 sigmoidal units fully connects 22 sensory input neurons to 2 motor output neurons ( figure 3) [7].…”

Section: Predators and Prey: Neural Network Controllersmentioning

confidence: 99%

See 1 more Smart Citation

Neuro-evolution Methods for Designing Emergent Specialization

Nitschke

Advances in Artificial Life

View full text Add to dashboard Cite

Abstract. This research applies the Collective Specialization NeuroEvolution (CONE) method to the problem of evolving neural controllers in a simulated multi-robot system. The multi-robot system consists of multiple pursuer (predator) robots, and a single evader (prey) robot. The CONE method is designed to facilitate behavioral specialization in order to increase task performance in collective behavior solutions. PursuitEvasion is a task that benefits from behavioral specialization. The performance of prey-capture strategies derived by the CONE method, are compared to those derived by the Enforced Sub-Populations (ESP) method. Results indicate that the CONE method effectively facilitates behavioral specialization in the team of pursuer robots. This specialization aids in the derivation of robust prey-capture strategies. Comparatively, ESP was found to be not as appropriate for facilitating behavioral specialization and effective prey-capture behaviors.

show abstract

Cooperative Coevolution of Control for a Real Multirobot System

Gomes

Duarte

Mariano

et al. 2016

Parallel Problem Solving From Nature – PPSN XIV

View full text Add to dashboard Cite

The potential of cooperative coevolutionary algorithms (CCEAs) as a tool for evolving control for heterogeneous multirobot teams has been shown in several previous works. The vast majority of these works have, however, been confined to simulation-based experiments. In this paper, we present one of the first demonstrations of a real multirobot system, operating outside laboratory conditions, with controllers synthesised by CCEAs. We evolve control for an aquatic multirobot system that has to perform a cooperative predator-prey pursuit task. The evolved controllers are transferred to real hardware, and their performance is assessed in a non-controlled outdoor environment. Two approaches are used to evolve control: a standard fitness-driven CCEA, and novelty-driven coevolution. We find that both approaches are able to evolve teams that transfer successfully to the real robots. Novelty-driven coevolution is able to evolve a broad range of successful team behaviours, which we test on the real multirobot system.

show abstract

Designing emergent cooperation: a pursuit–evasion game case study

Cited by 7 publications

References 12 publications

Evolving team behaviors with specialization

Evolving team behaviors with specialization

Neuro-evolution Methods for Designing Emergent Specialization

Cooperative Coevolution of Control for a Real Multirobot System

Contact Info

Product

Resources

About