The Suitable Timing of Visual Sensing in Error Recovery Using Task Stratification and Error Classification

Abstract

Judgment of errors for recovery is performed during execution of the system. Ideally, it is desirable for the judgment to be performed at several times. However, in that case, many sensors would be needed and it would lead to disturbing the workflow. Therefore, it is important to be able to judge an error efficiently in the most suitable timing and within a few attempts. This paper describes a method for efficient timing of visual sensing for error recovery.

Using Importance Ranks to Derive Suitable Timing of Visual Sensing in Manipulation Task Containing Error Recovery

“…We researched the timing appropriate to visual sensing in skill sequences with error recovery in Nakamura et al [10]. It is efficient that a visual sensing is performed by considering the difficulty in accomplishing a skill primitive, as shown in Case 4 of Section 4 of Nakamura et al [10]. The degree of necessity of a visual sensing is derived based on the consideration of the following idea in this paper.…”