Error recovery using task stratification and error classification for manipulation robots in various fields

Abstract

Dexterous manipulation is an important function for working robots. Manipulator tasks such as grasping, assembly and disassembly can generally be divided into several motion primitives. We call such motion primitives "skills" and explain how most manipulator tasks can be composed of sequences of these skills. We will address the issues involved with various types of robots such as maintenance robots and service robots. We have considered hierarchizing the manipulation tasks of these robots since their tasks have become more complex than ever before. Additionally, as errors are seen likely to increase in complex tasks, it is important to implement effective error recovery technology. This paper presents our proposal for a new type of error recovery that uses the concepts of task stratification and error classification which can be expressed specifically using flow charts.

Estimation and Categorization of Errors in Error Recovery Using Task Stratification and Error Classification

“…We proposed a new type of error recovery method that uses both forward and backward passes in Ref. 6. Figure 1 shows a diagram for the basic concept of our error recovery.…”

“…3). For example, consider the following order of priority for error causes: 6 . This is an example derived from a case where p 1 = 30%, p 2 = 25%, p 3 = 20%, p 4 = 12%, p 5 = 8% and p 6 = 5%.…”

“…We propose an approach to error recovery that uses the concepts of task stratification and error classification. 5,6 With our error recovery technique, a highly reliable system expression is derived by analyzing the error and estimating the cause, and the work process continues based on the expressions of the corrected system.…”

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

“…7 and proposed a new method of error recovery in Ref. 8. These methods are based on the concepts of task stratification and error classification.…”

“…[1][2][3][4][5][6] We have proposed an error recovery method using the concepts of task stratification and error classification. 7,8 In a robot system with error recovery capability, sensing is performed by using vision systems for the judgment of errors mainly at important points. For the purpose of evading errors as much as possible, it is desirable to perform visual sensing for error judgments at several times.…”