Initialisation and Estimation Methods for Batch Optimisation of Inertial/Visual SLAM
2013 (English)Report (Other academic)
Simultaneous Localisation and Mapping (SLAM) denotes the problem of jointly localizing a moving platform and mapping the environment. This work studies the SLAM problem using a combination of inertial sensors, measuring the platform's accelerations and angular velocities, and a monocular camera observing the environment. We formulate the SLAM problem on a nonlinear least squares (NLS) batch form, whose solution provides a smoothed estimate of the motion and map. The NLS problem is highly nonconvex in practice, so a good initial estimate is required. We propose a multi-stage iterative procedure, that utilises the fact that the SLAM problem is linear if the platform's rotations are known. The map is initialised with camera feature detections only, by utilising feature tracking and clustering of feature tracks. In this way, loop closures are automatically detected. The initialization method and subsequent NLS refinement is demonstrated on both simulated and real data.
Place, publisher, year, edition, pages
2013. , 15 p.
LiTH-ISY-R, ISSN 1400-3902 ; 3065
Simultaneous localisation and mapping, optimisation, inertial measurement unit, monocular camera
IdentifiersURN: urn:nbn:se:liu:diva-97278ISRN: LiTH-ISY-R-3065OAI: oai:DiVA.org:liu-97278DiVA: diva2:646572