Channon, AD and Jolley, B (2017) Toward Evolving Robust, Deliberate Motion Planning With HyperNEAT. In: Proceedings of the IEEE Symposium Series on Computational Intelligence 2017. IEEE, 3488 - 3495 (8). ISBN 978-1-5386-2725-9 (In Press)

[img] Text
ieeeALife2017alt.pdf - Accepted Version
Restricted to Repository staff only

Download (5MB)


Previous works have used a novel hybrid network architecture to create deliberative behaviours to solve increasingly challenging tasks in two-dimensional and threedimensional artificial worlds. At the foundation of each is a static hand-designed neural network for robust and deliberative motion planning. This paper presents results from replacing the hand-designed motion-planning subnetwork with HyperNEAT. Simulations are run on the original two-dimensional world with, and without, relative position inputs and a multievaluation fitness function, thus assessing the relative performance of each strategy. The focus of this work is on solutions adaptable to general environments; following evolution, each strategy's performance is evaluated on 10,000 world configurations. The results demonstrate that although HyperNEAT was not able to achieve as robust results as a hand-design approach, the best strategy was comparable, with just a 3-4% drop in performance. Relative position inputs and the multievaluation fitness function were both significant in achieving superior general performance, compared to those simulations without.

Item Type: Book Section
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Natural Sciences > School of Computing and Maths
Depositing User: Symplectic
Date Deposited: 20 Dec 2017 09:22
Last Modified: 20 Dec 2017 09:22

Actions (login required)

View Item View Item