Back to Search
Start Over
On the effects of pruning on evolved neural controllers for soft robots
- Source :
- GECCO Companion
- Publication Year :
- 2021
- Publisher :
- Association for Computing Machinery, Inc, 2021.
-
Abstract
- Artificial neural networks (ANNs) are commonly used for controlling robotic agents. For robots with many sensors and actuators, ANNs can be very complex, with many neurons and connections. Removal of neurons or connections, i.e., pruning, may be desirable because (a) it reduces the complexity of the ANN, making its operation more energy efficient, and (b) it might improve the generalization ability of the ANN. Whether these goals can actually be achieved in practice is however still not well known. On the other hand, it is widely recognized that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this work, we consider the case of Voxel-based Soft Robots, a kind of robots where sensors and actuators are distributed over the body and that can be controlled with ANNs optimized by means of neuroevolution. We experimentally characterize the effect of different forms of pruning on the effectiveness of neuroevolution, also in terms of generalization ability of the evolved ANNs. We find that, with some forms of pruning, a large portion of the connections can be pruned without strongly affecting robot capabilities. We also observe sporadic improvements in generalization ability.
- Subjects :
- Neuroevolution
Artificial neural network
Computer science
business.industry
Generalization
Synaptic pruning
Computer Science::Neural and Evolutionary Computation
Evolutionary robotics
synaptic pruning
neuroevolution
Computer Science::Robotics
evolutionary robotics
medicine.anatomical_structure
medicine
Robot
evolutionary robotic
Artificial intelligence
Pruning (decision trees)
business
Computer Science::Databases
Efficient energy use
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- GECCO Companion
- Accession number :
- edsair.doi.dedup.....50e5179f89652466d3ffe695c6482c04