Towards Robust Task Execution for Domestic Service Robots

Abstract

In the field of domestic service robots, recovery from faults

is crucial to promote user acceptance. In this context we focus

in particular on some specific faults, which arise from the

interaction of a robot with its real world environment.

Even a well-modelled robot may fail to perform its tasks successfully

due to unexpected situations, which occur while interacting.

These situations occur as deviations of properties

of the objects (manipulated by the robot) from their expected

values. Hence, they are experienced by the robot as external

faults.

In this paper we present two approaches to handle external

faults which result from inadequate descriptions of a planner

operator. In both approaches we assume that the robot is

able to detect the occurrence of the fault at the planning level

by monitoring the effects of an executed action. In our work

we limit the scope of the sources of external faults to natural

physical phenomena. Hence, we do not consider cases

in which an external agent (e.g. another robot, a human being)

is the cause of a detected fault. We apply the proposed

approaches to scenarios in which the robot performs a manipulation

task (pick and place).