Deriving minimal sensory configurations for evolved cooperative robot teams

Watson, James; Nitschke, Geoff

doi:10.1109/cec.2015.7257271

“…In swarm robotics, only a couple of studies are available that use concurrent design methods to design a robot swarm. Watson & Nitschke (2015) studied the impact of the number of sensors and their position on the robot to select the minimal sensor configuration of individual robot for a collective construction task. They achieved that by manually selecting six different sensors configurations and generating six instances of control software in the form of artificial neural networks using HyperNeat.…”

Section: State Of the Artmentioning

confidence: 99%

“…These concurrent design methods have significantly increased the performance and versatility of the designed robots. In swarm robotics, only a few research articles have been published that studied the concurrent automatic design of control software and configuration of the hardware (Watson & Nitschke, 2015). Details are provided in the STATE OF THE ART section.…”

Section: Introductionmentioning

confidence: 99%

Concurrent design of control software and configuration of hardware for robot swarms under economic constraints

Salman

¹

,

Ligot

²

,

Birattari

³

2019

PeerJ Computer Science

View full text Add to dashboard Cite

Designing a robot swarm is challenging due to its self-organized and distributed nature: complex relations exist between the behavior of the individual robots and the collective behavior that results from their interactions. In this paper, we study the concurrent automatic design of control software and the automatic configuration of the hardware of robot swarms. We introduce Waffle, a new instance of the AutoMoDe family of automatic design methods that produces control software in the form of a probabilistic finite state machine, configures the robot hardware, and selects the number of robots in the swarm. We test Waffle under economic constraints on the total monetary budget available and on the battery capacity of each individual robot comprised in the swarm. Experimental results obtained via realistic computer-based simulation on three collective missions indicate that different missions require different hardware and software configuration, and that Waffle is able to produce effective and meaningful solutions under all the experimental conditions considered.

show abstract

“…In swarm robotics, only a couple of studies are available that use concurrent design methods to design a robot swarm. Watson and Nitschke (2015) studied the impact of the number of sensors and their position on the robot to select the minimal sensor configuration of individual robot for a collective construction task. They achieved that by manually selecting six different sensors configurations and generating six instances of control software in the form of artificial neural networks using HyperNeat.…”

Section: State Of the Artmentioning

confidence: 99%

“…These concurrent design methods have significantly increased the performance and versatility of the designed robots. In swarm robotics, only a few research articles have been published that studied the concurrent automatic design of control software and configuration of the hardware (Watson and Nitschke, 2015). Details are provided in the STATE OF THE ART section.…”

Section: Introductionmentioning

confidence: 99%

Peer Review #1 of "Concurrent design of control software and configuration of hardware for robot swarms under economic constraints (v0.1)"

2019

0

View full text Add to dashboard Cite

Designing a robot swarm is challenging due to its self-organized and distributed nature: complex relations exist between the behavior of the individual robots and the collective behavior that results from their interactions. In this paper, we study the concurrent automatic design of control software and the automatic configuration of the hardware of robot swarms. We introduce Waffle, a new instance of the AutoMoDe family of automatic design methods that produces control software in the form of a probabilistic finite state machine, configures the robot hardware, and selects the number of robots in the swarm. We test Waffle under economic constraints on the total monetary budget available and on the battery capacity of each individual robot comprised in the swarm. Experimental results obtained via realistic computer-based simulation on three collective missions indicate that different missions require different hardware and software configuration, and that Waffle is able to produce effective and meaningful solutions under all the experimental conditions considered.

show abstract