Transferability in the Automatic Off-Line Design of Robot Swarms: From Sim-to-Real to Embodiment and Design-Method Transfer Across Different Platforms

Automatic off-line design is an attractive approach to implementing robot swarms. In this approach, a designer specifies a mission to be accomplished by the swarm, and an optimization process generates suitable control software for the individual robots through computer-based simulations. Most relev...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters Vol. 9; no. 3; pp. 2758 - 2765
Main Authors: Kegeleirs, Miquel, Ramos, David Garzon, Hasselmann, Ken, Garattoni, Lorenzo, Francesca, Gianpiero, Birattari, Mauro
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.03.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Automatic design
Behavioral sciences
Design methodology
evolutionary robotics
methods and tools for robot system design
Optimization
Platforms
Reinforcement learning
Robot sensing systems
Robots
Software
Swarm robotics
transferability
ISSN:2377-3766, 2377-3766
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic off-line design is an attractive approach to implementing robot swarms. In this approach, a designer specifies a mission to be accomplished by the swarm, and an optimization process generates suitable control software for the individual robots through computer-based simulations. Most relevant literature has focused on effectively transferring control software from simulation to physical robots. Here, we investigate <list list-type="ordered"><list-item> 1) whether the design methods that generate control software are transferable across robot platforms and </list-item> <list-item> 2) whether control software generated via such methods is itself transferable. </list-item> We experiment with two ground mobile platforms with equivalent functional capabilities. Our measure of transferability is based on the performance drop observed when control software and/or design methods are ported from one platform to another. Results indicate that, while the control software generated via automatic design is possibly transferable, better performance can be achieved when a transferable method is directly applied to the new platform.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2024.3360013