Developmental Context-driven Robot learning
Robots and robotics are becoming increasingly important outside their normal industrial applications, and are seen as having enormous potential for social good, as well as industrial and economic value. The DeCoRo research project explores real-time developmental learning in a humanoid robot on practical real-world manipulation tasks. Such learning may help robotic systems move towards fulfilling their promise for improving lives and living.
This Marie Curie Intra-European Fellowship project is carried out by Dr. Martin F. Stoelen, under the supervision of Prof. Angelo Cangelosi, both part of the Centre for Robotics and Neural Systems (CRNS) at Plymouth University, UK.
The principal objectives of this project are to study how the full sensorial context of an embodied robot platform can be used to drive behaviour; how such behaviour can be self-organized in real-time to enable learning in dynamic (and learning) contexts; and how to not only ground existing symbols in the sensorimotor interaction, but also adapt the structure of the neural substrate to enable a development of the set of symbols used.
Dr. Martin F. Stoelen has research interests in embodied cognition, human factors and assistive robotics. The scientist in charge, Prof. Angelo Cangelosi, is the director of the Centre for Robotics and Neural Systems (CRNS) at Plymouth University. Plymouth University research staff provides support on developmental learning algorithms and iCub experiments. Prof. Fabio Bonsignorio of the Biorobotics Institute, Scuola Superiore S. Anna, Italy, and CEO/founder of Heron Robots, assists on performance benchmarking and information-driven self-organization.
The project begun in September 2014, and will last until October 2016. We will try to use the blog to report on the progress of the project as we go along. Feel free to contact us if you have any questions, at martin [dot] stoelen [at] plymouth [dot] ac [dot] uk.