Adapting ROS Logs to Facilitate Transparency and Accountability in Service Robotics

Abstract

Understanding why a particular robot behavior was triggered is a cornerstone for having human-acceptable social robots. Thus, every robot action should be explained in order to audit, recognize, and control expected and unexpected behaviors using usual sources of information provided by robot software components. Enabling intelligibility goes through a correct translation of system logs. This paper presents an initial approach for arranging low-level knowledge extracted from logs available in the de facto standard for service robotics ROS in order to be useful for developers and regulators.