Active visual SLAM for robotic area coverage: Theory and experiment

TLDR

Robotic area coverage aims to explore and map a target area quickly, requiring minimally redundant overlap trajectories, but visual SLAM navigation drifts without loop closures, making coverage efficiency and navigation accuracy competing objectives. The study introduces a perception‑driven navigation algorithm that balances exploration and revisitation to solve the visual SLAM robotic area coverage problem. The algorithm uses a reward framework that incorporates SLAM localization uncertainty, coverage performance, and candidate region identification to balance exploration and revisitation. Experiments in simulation and real‑world underwater hull inspection demonstrate the algorithm’s effectiveness.

Abstract

This paper reports on an integrated navigation algorithm for the visual simultaneous localization and mapping (SLAM) robotic area coverage problem. In the robotic area coverage problem, the goal is to explore and map a given target area within a reasonable amount of time. This goal necessitates the use of minimally redundant overlap trajectories for coverage efficiency; however, visual SLAM’s navigation estimate will inevitably drift over time in the absence of loop closures. Therefore, efficient area coverage and good SLAM navigation performance represent competing objectives. To solve this decision-making problem, we introduce perception-driven navigation, an integrated navigation algorithm that automatically balances between exploration and revisitation using a reward framework. This framework accounts for SLAM localization uncertainty, area coverage performance, and the identification of good candidate regions in the environment for visual perception. Results are shown for both a hybrid simulation and real-world demonstration of a visual SLAM system for autonomous underwater ship hull inspection.