Ulster University Logo

A Robot that Autonomously Improves Skills by Evolving Computational Graphs

Riano, Lorenzo and McGinnity, TM (2012) A Robot that Autonomously Improves Skills by Evolving Computational Graphs. In: 2012 IEEE Congress on Evolutionary Computation, Brisbane, Australia. IEEE Press. 8 pp. [Conference contribution]

PDF - Accepted Version


We propose an evolutionary algorithm to au- tonomously improve the performances of a robotics skill. The algorithm extends a previously proposed graphical evolutionary skills building approach to allow a robot to autonomously collect use cases where a skill fails and use them to improve the skill. Here we define a computational graph as a generic model to hierarchically represent skills and to modify them. The computational graph makes use of embedded neural networks to create generic skills. We tested our proposed algorithm on a real robot implementing a “move to reach” action. Four experiments show the evolution of the computational graph as it is adapted to solve increasingly complex problems.

Item Type:Conference contribution (Paper)
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Intelligent Systems
Research Institutes and Groups:Computer Science Research Institute > Intelligent Systems Research Centre
Computer Science Research Institute
ID Code:21537
Deposited By: Dr Lorenzo Riano
Deposited On:10 Jul 2012 10:39
Last Modified:09 Dec 2015 11:03

Repository Staff Only: item control page