Cooperative Coevolution of Control for a Real Multirobot System

Gomes, Jorge; Duarte, Miguel; Mariano, Pedro; Christensen, Anders Lyhne

doi:10.1007/978-3-319-45823-6_55

Cited by 12 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental and simulation parameters are given in table 3. Parameters associated with the learning mechanism are given in table 4. e values for LR initial and LR max where selected following limited empirical exploration.…”

Section: Methodsmentioning

confidence: 99%

“…Finally in social learning, robots can exchange information during a lifetime. e relative bene ts of mixing the di erent types of adaptation have been studied both in simulation [3,6] and hardware [4,[10][11][12]. Typically, experiments are conducted in single environment related to a speci c task, therefore the role of the environment in in uencing the result is not made explicit.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

Steyven

Hart

Paechter

2017

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in in uencing the e ectiveness of each type of learning is not well understood. In this paper, we address this question by analysing the performance of a swarm in a range of simulated, dynamic environments where a distributed evolutionary algorithm for evolving a controller is augmented with a number of di erent individual learning mechanisms. e learning mechanisms themselves are de ned by parameters which can be either xed or inherited. We conduct experiments in a range of dynamic environments whose characteristics are varied so as to present di erent opportunities for learning. Results enable us to map environmental characteristics to the most e ective learning algorithm.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

Steyven

Hart

Paechter

2017

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

show abstract

“…Most of these works use global information about the position of the sheep swarm and also rely on a single shepherd or a single sheep/item of prey [13][14][15][16]. That limits the real applicability of the behaviors obtained or even the possibility of effectively parallelizing this task.…”

Section: Literature Reviewmentioning

confidence: 99%

Obtaining emergent behaviors for swarm robotics singling with deep reinforcement learning

et al. 2023

View full text Add to dashboard Cite

Isolating (singling) an individual from a group can be essential for protection, rescue or capture tasks. In this paper a system with multiple shepherds who must coordinate the sheep to achieve a specific singleness is proposed. We present a realistically modeled system that will be finally tested in a real robotic system. We want to encourage the adaptability of the system and provide different solutions by promoting the emergence of the swarm. In this line we will focus on the use of reinforcement learning, avoiding a manual design of the behavior in order to not restrict the resulting behaviors and to facilitate their adaptation. A detailed MDP model will be specified as well as the keys to reduce its dimensionality and facilitate its training.We will check the results of the obtained singling policy with respect to a greedy policy and focus on evaluating different behavioral strategies that can solve the problem in different ways. In addition, one of the obtained policies will be analyzed in detail to check both its robustness and its scalability with respect to the number of shepherds and sheep. This policy will be finally tested on a physical robotic swarm.

show abstract

“…The predator-prey pursuit environment has been used by researchers since 1985 [1] to investigate a host of topics including various aspects of group dynamics [25,46], pursuit strategies [3,47], escape/evasion strategies [27,41,48], and multi-agent systems [18][19][20]49] to name a few. The last portion of this article discusses a set of proposed manipulations to the predator-prey pursuit environment to investigate potential simulated tactical scenarios that easily map to a physical domain.…”

Section: Adaptation Of the Predator-prey Pursuit Environment To Tacti...mentioning

confidence: 99%

Adapting the Predator-Prey Game Theoretic Environment to Army Tactical Edge Scenarios with Computational Multiagent Systems

Asher¹,

Zaroukian²,

Barton³

2018

EasyChair Preprints

View full text Add to dashboard Cite

The historical origins of the game theoretic predator-prey pursuit problem can be traced back to Benda, et al., 1985 [1]. Their work adapted the predator-prey ecology problem into a pursuit environment which focused on the dynamics of cooperative behavior between predator agents. Modifications to the predator-prey ecology problem [2] have been implemented to understand how variations to predator [3] and prey [3][4][5] attributes, including communication [6], can modify dynamic interactions between entities that emerge within that environment [7][8][9]. Furthermore, the predator-prey pursuit environment has become a testbed for simulation experiments with computational multiagent systems [10][11][12]. This article extends the theoretical contributions of previous work by providing 1) additional variations to predator and prey attributes for simulated multiagent systems in the pursuit problem, and 2) military-relevant predator-prey environments simulating highly dynamic, tactical edge scenarios that Soldiers might encounter on future battlefields. Through this exploration of simulated tactical edge scenarios with computational multiagent systems, Soldiers will have a greater chance to achieve overmatch on the battlefields of tomorrow.

show abstract

Cooperative Coevolution of Control for a Real Multirobot System

Cited by 12 publications

References 20 publications

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

Obtaining emergent behaviors for swarm robotics singling with deep reinforcement learning

Adapting the Predator-Prey Game Theoretic Environment to Army Tactical Edge Scenarios with Computational Multiagent Systems

Contact Info

Product

Resources

About