Abstract
We construct and investigate a strongly embodied evolutionary system, where not only the controllers but also the morphologies undergo evolution in an on-line fashion. In these studies, we have been using various types of robot morphologies and controller architectures in combination with several learning algorithms, e.g. evolutionary algorithms, reinforcement learning, simulated annealing, and HyperNEAT. This hands-on experience provides insights and helps us elaborate on interesting research directions for future development.
| Original language | English |
|---|---|
| Title of host publication | GECCO '17 |
| Subtitle of host publication | Proceedings of the Genetic and Evolutionary Computation Conference Companion |
| Publisher | ACM |
| Pages | 1735-1741 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781450349390 |
| DOIs | |
| Publication status | Published - Jul 2017 |
Keywords
- Evolutionary robotics
- Gait learning
- Indirect encoding
- Lamarckian evolution
- On-line evolution
Fingerprint
Dive into the research topics of 'Acquiring moving skills in robots with evolvable morphologies: Recent results and outlook'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver