Accession Number:

AD1042903

Title:

Autonomous Fault Detection for Performance Bugs in Component Based Robotic Systems

Descriptive Note:

OSTP Journal Article

Corporate Author:

Bielefeld Bielefeld Germany

Personal Author(s):

Report Date:

2016-12-01

Pagination or Media Count:

7.0

Abstract:

We present a novel fault detection method for application in component-based robotic systems. In contrast to existing work, our method specifically addresses faults in the software system of the robot using a data-driven methodology which exploits the inter-process communication of the system. This enables an application of the approach without expert knowledge or availability of complex software models. We specifically focus on performance bugs, which slowly degrade the performance of the system and are thereby harder to detect but also most valuable for automatic recovery. Using a data set recorded on a RoboCupHome platform we demonstrate the performance and applicability of our method and analyze the types of faults that can be detected by the method.

Subject Categories:

  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE