The Shortcomings of Force-from-Motion in Robot Learning
This addresses a fundamental problem in robotic manipulation for researchers and practitioners, but it is incremental as it critiques existing methods without presenting new experimental results.
The paper argues that current robot learning approaches, which focus on motion-centric action spaces, fail to explicitly control physical interactions, and it advocates for more interaction-explicit action spaces to address this limitation.
Robotic manipulation requires accurate motion and physical interaction control. However, current robot learning approaches focus on motion-centric action spaces that do not explicitly give the policy control over the interaction. In this paper, we discuss the repercussions of this choice and argue for more interaction-explicit action spaces in robot learning.