Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots

Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning...

Full description

Saved in:
Bibliographic Details
Published inKnowledge engineering review Vol. 37
Main Authors Nadizar, Giorgia, Medvet, Eric, Huse Ramstad, Hola, Nichele, Stefano, Pellegrino, Felice Andrea, Zullich, Marco
Format Journal Article
LanguageEnglish
Published Cambridge, UK Cambridge University Press 01.01.2022
Subjects
Actuators
Artificial neural networks
Brain research
Complexity
Controllers
Energy consumption
Locomotion
Metabolism
Nervous system
Network topologies
Neural networks
Neurons
Optimization
Pruning
Robots
Robust control
Soft robotics
Online AccessGet full text

Cover

More Information
Summary:Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.
ISSN:0269-8889
1469-8005
DOI:10.1017/S0269888921000151