On the dynamics of small continuous-time recurrent neural networks
Adaptive Behavior - Special issue on computational neuroethology
Gait Adaptation in a Quadruped Robot
Autonomous Robots
Evolving neural networks through augmenting topologies
Evolutionary Computation
A Taxonomy for artificial embryogeny
Artificial Life
Evolving modular genetic regulatory networks
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Compositional pattern producing networks: A novel abstraction of development
Genetic Programming and Evolvable Machines
A robot that walks; emergent behaviors from a carefully evolved network
Neural Computation
Picbreeder: evolving pictures collaboratively online
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
A case study on the critical role of geometric regularity in machine learning
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Evolving policy geometry for scalable multiagent learning
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Evolving Static Representations for Task Transfer
The Journal of Machine Learning Research
Abandoning objectives: Evolution through the search for novelty alone
Evolutionary Computation
Evolving the walking behaviour of a 12 DOF quadruped using a distributed neural architecture
BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology
Evolution of central pattern generators for bipedal walking in areal-time physics environment
IEEE Transactions on Evolutionary Computation
On the Performance of Indirect Encoding Across the Continuum of Regularity
IEEE Transactions on Evolutionary Computation
Single-unit pattern generators for quadruped locomotion
Proceedings of the 15th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
The ambulatory capabilities of legged robots offer the potential for access to dangerous and uneven terrain without a risk to human life. However, while machine learning has proven effective at training such robots to walk, a significant limitation of such approaches is that controllers trained for a specific robot are likely to fail when transferred to a robot with a slightly different morphology. This paper confronts this challenge with a novel strategy: Instead of training a controller for a particular quadruped morphology, it evolves a special function (through a method called HyperNEAT) that takes morphology as input and outputs an entire neural network controller fitted to the specific morphology. Once such a relationship is learned the output controllers are able to work on a diversity of different morphologies. Highlighting the unique potential of such an approach, in this paper a neural controller evolved for three different robot morphologies, which differ in the length of their legs, can interpolate to never-seen intermediate morphologies without any further training. Thus this work suggests a new research path towards learning controllers for whole ranges of morphologies: Instead of learning controllers themselves, it is possible to learn the relationship between morphology and control.