Efficient View-Based SLAM Using Visual Loop Closures
Ian Mahon · Stefan B. Williams · Oscar R. Pizarro · Matthew Johnson-Roberson
TL;DR
An efficient visual SLAM method uses stereo loop closures and Cholesky updates to correct underwater vehicle trajectories during large sponge bed surveys.
BRIEF
Robots that map large areas need to correct drift in their position estimates whenever they recognize a place they have already seen. This work builds a SLAM method on the viewpoint augmented navigation framework, which uses an extended information filter. By maintaining and updating a Cholesky factor of the information matrix, the method can efficiently recover state estimates and covariances. It is tested on data from an autonomous underwater vehicle surveying sponge beds, where stereo vision loop closures correct a trajectory from dead reckoning sensors.
Abstract
This paper presents a simultaneous localization and mapping algorithm suitable for large-scale visual navigation. The estimation process is based on the viewpoint augmented navigation (VAN) framework using an extended information filter. Cholesky factorization modifications are used to maintain a factor of the VAN information matrix, enabling efficient recovery of state estimates and covariances. The algorithm is demonstrated using data acquired by an autonomous underwater vehicle performing a visual survey of sponge beds. Loop-closure observations produced by a stereo vision system are used to correct the estimated vehicle trajectory produced by dead reckoning sensors.