Co-active Learning to Adapt Humanoid Movement for Manipulation
This work addresses robot movement adaptation for manipulation in varied environments and user-specific needs, representing an incremental improvement over traditional motion generation methods.
The paper tackles the problem of adapting robot movement for manipulation tasks under novel environmental constraints and user preferences by proposing a co-active learning framework that incorporates human feedback. Experiments on a humanoid platform validate the approach, though no concrete numbers are provided.
In this paper we address the problem of robot movement adaptation under various environmental constraints interactively. Motion primitives are generally adopted to generate target motion from demonstrations. However, their generalization capability is weak while facing novel environments. Additionally, traditional motion generation methods do not consider the versatile constraints from various users, tasks, and environments. In this work, we propose a co-active learning framework for learning to adapt robot end-effector's movement for manipulation tasks. It is designed to adapt the original imitation trajectories, which are learned from demonstrations, to novel situations with various constraints. The framework also considers user's feedback towards the adapted trajectories, and it learns to adapt movement through human-in-the-loop interactions. The implemented system generalizes trained motion primitives to various situations with different constraints considering user preferences. Experiments on a humanoid platform validate the effectiveness of our approach.