Automated Robot Recovery from Assumption Violations of High-Level Specifications

TL;DR

This paper introduces a synthesis-based framework that allows robots to automatically recover from assumption violations during task execution by repairing and adapting their skills without human intervention.

Contribution

It proposes a novel method for automatic robot recovery from environment assumption violations using synthesis-based repair of robot skills.

Findings

Successfully demonstrated on Hello Robot Stretch in a factory scenario

Automatically detects and relaxes environment safety assumptions

Synthesizes new robot skills for task completion

Abstract

This paper presents a framework that enables robots to automatically recover from assumption violations of high-level specifications during task execution. In contrast to previous methods relying on user intervention to impose additional assumptions for failure recovery, our approach leverages synthesis-based repair to suggest new robot skills that, when implemented, repair the task. Our approach detects violations of environment safety assumptions during the task execution, relaxes the assumptions to admit observed environment behaviors, and acquires new robot skills for task completion. We demonstrate our approach with a Hello Robot Stretch in a factory-like scenario.