Instinct-driven Dynamic Hardware Reconfiguration: Evolutionary Algorithm Optimized Compression for Autonomous Sensory Agents

Authors:
Ahmed Hallawa, Jaro De Roose, Martin Andraud, Marian Verhelst, and Gerd Ascheid
Book Title:
Proceedings of the Genetic and Evolutionary Computation Conference Companion
Series:
GECCO '17
Publisher:
ACM
Address:
New York, NY, USA
Pages:
1727–1734
Date:
July 2017
ISBN:
978-1-45034-939-0
DOI:
10.1145/3067695.3084202
Language:
English

BibTeX

@inproceedings{hallawa17b,
author = {Ahmed Hallawa, Jaro De Roose, Martin Andraud, Marian Verhelst, and Gerd Ascheid},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference Companion},
title = {Instinct-driven Dynamic Hardware Reconfiguration: Evolutionary Algorithm Optimized Compression for Autonomous Sensory Agents},
year = {2017},
month = {jul},
address = {New York, NY, USA},
pages = {1727-1734},
ISBN= {978-1-45034-939-0},
publisher = {ACM},
series = {GECCO '17},
doi = {10.1145/3067695.3084202},
}

Abstract

Advancement in miniaturization of autonomous sensory agents can play a profound role in many applications such as the exploration of unknown environments, however, due to their miniature size, power limitations poses a severe challenge. In this paper, and inspired from biological instinctive behaviour, we introduce an instinct-driven dynamic hardware reconfiguration design scheme using evolutionary algorithms on behaviour trees. Moreover, this scheme is projected on an application scenario of autonomous sensory agents exploring an inaccessible dynamic environment. In this scenario, agent's compression behaviour -introduced as an instinct- is critical due to the limited energy available on the agents. This emphasises the role of optimization of agents resources through dynamic hardware reconfiguration. In that regard, the presented approach is demonstrated using two compression techniques: Zero-order hold and Wavelet compression. Behavioural and hardware-based power models of these techniques, integrated with behaviour trees (BT), are implemented to facilitate off-line learning of the optimum on-line behaviour, thus, facilitating dynamic reconfiguration of agents hardware.

 

Download

No download found.

News >> News >> News

New European initiative TETRAMAX has officially been kicked-off!

With its kick-off meeting on 19 September in Aachen, TETRAMAX (TEchnology TRAnsfer via

ICE invites applications for a Postdoc position

Area: Application Specific Computing Systems and Hardware Architectures

User login

Login

Forgot your password?