A stereo visual navigation method for docking autonomous underwater vehicles

Abstract

AbstractRecovering and recharging autonomous underwater vehicles (AUVs) on a regular basis allows for long‐term underwater activities. This research provides a vision‐based navigation strategy for AUVs to independently identify and reconstruct the docking station (DS). The proposed framework includes a light beacon detection approach, a filter‐based light beacon matching method, and a fusion pose estimation method for DS positioning. Four green LED light beacons are mounted symmetrically on the docking ring, enabling the stereo camera to observe them from close range. A method for detecting light beacons is proposed that assures detection accuracy by identifying false positives. On a single frame from a stereo camera, filter‐based matching follows the light beacons precisely. In addition, we construct a position estimate method that significantly improves accuracy and efficiency by consisting of analyzation and iteration. A series of virtual and real‐world experiments demonstrate that our methodology can provide AUVs with reliable docking navigation.