Unsupervised Motion Retargeting for Human-Robot Imitation
This addresses the challenge of human-robot imitation for robotics applications, but it is incremental as it adapts existing unpaired translation methods.
The paper tackles the problem of translating human joint motions to robot motions for imitation, proposing an encoder-decoder neural network for unpaired domain-to-domain translation to overcome the scarcity of paired data.
This early-stage research work aims to improve online human-robot imitation by translating sequences of joint positions from the domain of human motions to a domain of motions achievable by a given robot, thus constrained by its embodiment. Leveraging the generalization capabilities of deep learning methods, we address this problem by proposing an encoder-decoder neural network model performing domain-to-domain translation. In order to train such a model, one could use pairs of associated robot and human motions. Though, such paired data is extremely rare in practice, and tedious to collect. Therefore, we turn towards deep learning methods for unpaired domain-to-domain translation, that we adapt in order to perform human-robot imitation.