Jolley, B and Channon, AD ORCID: https://orcid.org/0000-0001-9224-4931 (2018) Evolving Robust, Deliberate Motion Planning With a Shallow Convolutional Neural Network. Proceedings of the 2018 Conference on Artificial Life. 536 - 543 (8).

[img]
Preview
Text
alife2018.pdf - Accepted Version

Download (302kB) | Preview

Abstract

Deep Convolutional Neural Networks (ConvNets) have seen great success on machine learning tasks in recent years but have shown difficulty with tasks that require long-term deliberative planning. Whereas, purpose-built hybrid network architectures have been able to solve increasingly challenging deliberate tasks in two-dimensional and three-dimensional artificial worlds. Starting from a purpose-built network and transitioning to a general architecture, like a deep ConvNet, may retain long-term deliberative planning while allowing greater flexibility in the task domain. This paper employs a standard genetic algorithm (GA) to train the weights of a ConvNet with a recurrent 3x3 filter to produce robust and deliberative motion planning. This technique resulted in an average of 98.97% completion over 10,000 runs in the most difficult deliberate task. This demonstrates that a shallow ConvNet with recurrent connections is capable of producing deliberate and robust motion planning. Further, the evolved ConvNet exhibits superior motion planning in the most challenging environments, when compared to the previous taskspecific motion-planning network.

Item Type: Article
Additional Information: This is the accepted author manuscript (AAM). The final published version (version of record) is available online via MIT Press at https://doi.org/10.1162/isal_a_00099 - please refer to any applicable terms of use of the publisher.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Depositing User: Symplectic
Date Deposited: 30 Aug 2018 13:48
Last Modified: 09 Dec 2019 11:21
URI: http://eprints.keele.ac.uk/id/eprint/5258

Actions (login required)

View Item View Item