Co-imitation: Learning Design and Behaviour by Imitation
Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki
Abstract
The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a robot for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state-distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.
BibTeX
@article{Rajani_Arndt_Blanco-Mulero_Luck_Kyrki_2023, title={Co-imitation: Learning Design and Behaviour by Imitation}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25764}, DOI={10.1609/aaai.v37i5.25764}, abstractNote={The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a robot for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems.
The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort.
This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state-distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Rajani, Chang and Arndt, Karol and Blanco-Mulero, David and Luck, Kevin Sebastian and Kyrki, Ville}, year={2023}, month={Jun.}, pages={6200-6208} }