Loading...
Evolution of Neural Networks for Physically Simulated Evolved Virtual Quadruped Creatures
Vaughan, Neil
Vaughan, Neil
Citations
Altmetric:
Advisors
Editors
Other Contributors
EPub Date
Publication Date
2018-07-07
Submitted Date
Collections
Files
Loading...
evcneil.pdf
Adobe PDF, 365.18 KB
Other Titles
Abstract
This work develops evolved virtual creatures (EVCs) using neuroevolution as the controller for movement and decisions within a 3D physics simulated environ-ment. Previous work on EVCs has displayed various behaviour such as following a light source. This work is focused on complexifying the range of behaviours available to EVCs. This work uses neuroevolution for learning specific actions combined with other controllers for making higher level decisions about which action to take in a given scenario. Results include analysis of performance of the EVCs in simulated physics environment. Various controllers are compared including a hard coded benchmark, a fixed topology feed forward artificial neural network and an evolving ANN subjected to neuroevolution by applying mutations in both topology and weights. The findings showed that both fixed topology ANNs and neuroevolution did successfully control the evolved virtual creatures in the distance travelling task.
Citation
Vaughan N. (2018). Evolution of neural networks for physically simulated evolved virtual quadruped creatures. In V. Vouloutsi et al. (Eds.) Biomimetic and biohybrid systems. Living Machines. Springer.
Publisher
Springer
Journal
Research Unit
PubMed ID
PubMed Central ID
Type
Conference Contribution
Language
en
Description
Series/Report no.
Lecture Notes in Computer Science, volume 10928
ISSN
EISSN
ISBN
9783319959719