Creative Adaptation through Learning

Abstract : Robots have transformed many industries, most notably manufacturing, and have the power to deliver tremendous benefits to society, for example in search and rescue, disaster response, health care, and transportation. They are also invaluable tools for scientific exploration of distant planets or deep oceans. A major obstacle to their widespread adoption in more complex environments and outside of factories is their fragility. While animals can quickly adapt to injuries, current robots cannot “think outside the box” to find a compensatory behavior when they are damaged: they are limited to their pre-specified self-sensing abilities, which can diagnose only anticipated failure modes and strongly increase the overall complexity of the robot. In this thesis, we propose a different approach that considers having robots learn appropriate behaviors in response to damage. However, current learning techniques are slow even with small, constrained search spaces. To allow fast and creative adaptation, we combine the creativity of evolutionary algorithms with the learning speed of policy search algorithms through three contributions: the behavioral repertoires, the damage recovery using these repertoires and the transfer of knowledge across tasks. Globally, this work aims to provide the algorithmic foundations that will allow physical robots to be more robust, effective and autonomous.
Document type :
Complete list of metadatas
Contributor : Abes Star <>
Submitted on : Friday, September 23, 2016 - 11:45:49 AM
Last modification on : Saturday, December 21, 2019 - 3:24:56 AM


  • HAL Id : tel-01265957, version 2


Antoine Cully. Creative Adaptation through Learning. Artificial Intelligence [cs.AI]. Université Pierre et Marie Curie - Paris VI, 2015. English. ⟨NNT : 2015PA066664⟩. ⟨tel-01265957v2⟩



Record views


Files downloads