Enough is Enough: Towards Autonomous Uncertainty-driven Stopping Criteria

TL;DR

This paper emphasizes the importance of autonomous stopping criteria in robotic exploration, analyzing a novel criterion based on active graph-SLAM to improve real-world deployment of such systems.

Contribution

It introduces and analyzes a new uncertainty-driven stopping criterion for autonomous exploration, addressing a gap in practical real-world robotic deployment.

Findings

The proposed criterion effectively determines when to stop exploration.

Analysis shows improved decision-making in active graph-SLAM.

Highlights the need for practical stopping strategies in real-world scenarios.

Abstract

Autonomous robotic exploration has long attracted the attention of the robotics community and is a topic of high relevance. Deploying such systems in the real world, however, is still far from being a reality. In part, it can be attributed to the fact that most research is directed towards improving existing algorithms and testing novel formulations in simulation environments rather than addressing practical issues of real-world scenarios. This is the case of the fundamental problem of autonomously deciding when exploration has to be terminated or changed (stopping criteria), which has not received any attention recently. In this paper, we discuss the importance of using appropriate stopping criteria and analyse the behaviour of a novel criterion based on the evolution of optimality criteria in active graph-SLAM.