Jackson, B and Channon, AD (2019) Neuroevolution of Humanoids that Walk Further and Faster with Robust Gaits. Artificial Life, 31. 543 - 550. ISSN 1530-9185

[thumbnail of A. Channon Neuroevolution.pdf]
A. Channon Neuroevolution.pdf - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview


Bipedal locomotion requires precise rhythm and balance. Here we demonstrate two fitness-function enhancements applied to OpenAI?s 3D Humanoid-v1 walking task using a replica of Salimans et al.?s evolution strategy (Salimans et al., 2017). The first enhancement reduces control cost, following a start-up period, and the second enhancement penalises poor balance. Individually, each enhancement results in improved gaits and doubles both median speed and median distance walked. Combining the two enhancements results in little further improvement in the absence of noise but is shown to produce gaits that are much more robust to noise in their actions, with median speed, distance and time two to five times those of the default and individual-enhancement gaits at an intermediate noise level.

Item Type: Article
Additional Information: © 2019 Massachusetts Institute of Technology Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license
Uncontrolled Keywords: Neuroevolution, Humanoids, Robust Gaits.
Subjects: H Social Sciences > H Social Sciences (General)
Q Science > Q Science (General)
Q Science > Q Science (General) > Q335 Artificial Intelligence
Q Science > QA Mathematics
Q Science > QC Physics
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Related URLs:
Depositing User: Symplectic
Date Deposited: 15 Jan 2020 11:42
Last Modified: 05 Mar 2020 13:48
URI: https://eprints.keele.ac.uk/id/eprint/7511

Actions (login required)

View Item
View Item