Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks

TL;DR

This paper introduces Recovery-Driven Development (RDD), a method for improving robot task robustness through hierarchical, iterative scripting and situated testing, demonstrated on a mobile manipulator for complex tasks.

Contribution

The paper presents RDD, a novel development process that simplifies creating robust robot task recovery strategies through hierarchical specification and iterative testing.

Findings

RDD enabled rapid development of robust recovery strategies.

The approach improved system robustness in complex robot tasks.

Successful validation on the FetchIt! Challenge platform.

Abstract

Robot task execution when situated in real-world environments is fragile. As such, robot architectures must rely on robust error recovery, adding non-trivial complexity to highly-complex robot systems. To handle this complexity in development, we introduce Recovery-Driven Development (RDD), an iterative task scripting process that facilitates rapid task and recovery development by leveraging hierarchical specification, separation of nominal task and recovery development, and situated testing. We validate our approach with our challenge-winning mobile manipulator software architecture developed using RDD for the FetchIt! Challenge at the IEEE 2019 International Conference on Robotics and Automation. We attribute the success of our system to the level of robustness achieved using RDD, and conclude with lessons learned for developing such systems.