Error growth in position estimation from noisy relative pose measurements
Robotics and Autonomous Systems
Gaussian Process Gauss-Newton for non-parametric simultaneous localization and mapping
International Journal of Robotics Research
Hi-index | 0.00 |
This paper addresses the problem of computing the trajectoryof a camera from sparse positional measurementsthat have been obtained from visual localisation, and densedifferential measurements from odometry or inertial sensors.A fast method is presented for fusing these two sourcesof information to obtain the maximum a posteriori estimateof the trajectory. A formalism is introduced for representingprobability density functions over Euclidean transformations,and it is shown how these density functions can bepropagated along the data sequence and how multiple estimatesof a transformation can be combined. A three-passalgorithm is described which makes use of these results toyield the trajectory of the camera.Simulation results are presented which are validatedagainst a physical analogue of the vision problem, and resultsare then shown from sequences of approximately 1,800frames captured from a video camera mounted on a go-kart.Several of these frames are processed using computer visionto obtain estimates of the position of the go-kart. The algorithmfuses these estimates with odometry from the entiresequence in 150 mS to obtain the trajectory of the kart.