Design and development of an inexpensive aquatic swarm robotics system

Costa, Vasco; Duarte, Miguel; Rodrigues, Tiago; Oliveira, Sancho; Christensen, Anders Lyhne

doi:10.1109/oceansap.2016.7485496

Cited by 12 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All basic code and libraries have been released under the GNU General Public License. Authors in [6] have made their research on aquatic swarm robots reproducible by providing the 3D printing models, CNC milling files and the developed software on Raspberry Pi. In this paper, we propose a framework that can be used to produce an arbitrary number of physical environments, not limited to robots.…”

Section: Background and Related Workmentioning

confidence: 99%

OPEB: Open physical environment benchmark for artificial intelligence

Mirzaei

Fathollahi

Givargis

2017

2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI)

View full text Add to dashboard Cite

Artificial Intelligence methods to solve continuouscontrol tasks have made significant progress in recent years. However, these algorithms have important limitations and still need significant improvement to be used in industry and realworld applications. This means that this area is still in an active research phase. To involve a large number of research groups, standard benchmarks are needed to evaluate and compare proposed algorithms. In this paper, we propose a physical environment benchmark framework to facilitate collaborative research in this area by enabling different research groups to integrate their designed benchmarks in a unified cloud-based repository and also share their actual implemented benchmarks via the cloud. We demonstrate the proposed framework using an actual implementation of the classical mountain-car example and present the results obtained using a Reinforcement Learning algorithm.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

OPEB: Open physical environment benchmark for artificial intelligence

Mirzaei

Fathollahi

Givargis

2017

2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI)

View full text Add to dashboard Cite

show abstract

“…Furthermore, the robots are equipped with a water temperature sensor. Additional details about the hardware and software platforms can be found in [15].…”

Section: A Robotic Platformmentioning

confidence: 99%

Application of swarm robotics systems to marine environmental monitoring

Duarte

Gomes

Costa

et al. 2016

OCEANS 2016 - Shanghai

Self Cite

View full text Add to dashboard Cite

Automated environmental monitoring in marine environments is currently carried out either by smallscale robotic systems, composed of one or few robots, or static sensor networks. In this paper, we propose the use of swarm robotics systems to carry out marine environmental monitoring missions. In swarm robotics systems, each individual unit is relatively simple and inexpensive. The robots rely on decentralized control and local communication, allowing the swarm to scale to hundreds of units and to cover large areas. We study the application of a swarm of aquatic robots to environmental monitoring tasks. In the first part of the study, we synthesize swarm control for a temperature monitoring mission and validate our results with a real swarm robotics system. Then, we conduct a simulation-based evaluation of the robots' performance over large areas and with large swarm sizes, and demonstrate the swarm's robustness to faults. Our results show that swarm robotics systems are suited for environmental monitoring tasks by efficiently covering a target area, allowing for redundancy in the data collection process, and tolerating individual robot faults.978-1-4673-9724-7/16/$31.00 ©2016 IEEE

show abstract

“…For our experiments, we use an aquatic multirobot system [1] that has been used in other evolutionary robotics studies in the past [3]. Each robot is a small (65 cm in length) differential drive mono-hull robot.…”

Section: Robotic Platformmentioning

confidence: 99%

“…For the evolutionary process, we used a two-dimensional simulation environment, where the robots are abstracted as circular objects with a certain heading and position 1 . The robot motion model was implemented based on simple measurements taken on the real robots, and did not include complex physics simulation or fluid dynamics.…”

Section: Simulationmentioning

confidence: 99%

Cooperative Coevolution of Control for a Real Multirobot System

Gomes

Duarte

Mariano

et al. 2016

Parallel Problem Solving From Nature – PPSN XIV

Self Cite

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

Design and development of an inexpensive aquatic swarm robotics system

Cited by 12 publications

References 13 publications

OPEB: Open physical environment benchmark for artificial intelligence

OPEB: Open physical environment benchmark for artificial intelligence

Application of swarm robotics systems to marine environmental monitoring

Cooperative Coevolution of Control for a Real Multirobot System

Contact Info

Product

Resources

About