Distance function based 6DOF localization for unmanned aerial vehicles in GPS denied environments

Abstract

This paper presents an algorithm for localizing an unmanned aerial vehicle (UAV) in GPS denied environments. Localization is performed with respect to a pre-built map of the environment represented using the distance function of a binary mosaic, avoiding the need for extraction and explicit matching of visual features. Edges extracted from images acquired by an on-board camera are projected to the map to compute an error metric that indicates the misalignment between the predicted and true pose of the UAV. A constrained extended Kalman filter (EKF) framework is used to generate an estimate of the full 6-DOF location of the UAV by enforcing the condition that the distance function values are zero when there is no misalignment. Use of an EKF also makes it possible to seamlessly incorporate information from any other system on the UAV, for example, from its auto-pilot, a height sensor or an optical flow sensor. Experiments using a hexarotor UAV both in a simulation environment and in the field are presented to demonstrate the effectiveness of the proposed algorithm.

A Monocular Indoor Localiser Based on an Extended Kalman Filter and Edge Images from a Convolutional Neural Network

“…where, R is the 3D rotation matrix representing the robot pose, R(ψ, θ, φ), and f is the focal length of the camera. Given a DF based map of the environment, it is now possible to obtain a measure for the "disparity" between expected and observed sensor observations by extracting the value of the DF at locations x zi [5].…”

“…The formulation of the EKF is done in a similar manner to our previous work proposed in [5]. The state vector x consists of 12 dimensions, namely, the 6-DOF robot pose, linear velocities ν, and angular velocities ω; x = r θ ν ω .…”

“…Then the variance in the direction of the closest edge point is found by multiplying the covariance matrix by the Jacobian of the DF w.r.t. the vector (x, y) to calculate (5). We then take the Zscore and reject outliers based on some level of uncertainty.…”

“…Therefore, these maps not only encode the occupied regions of the environment but also provide a continuous measure of the distance, a much richer representation of the environment. In [5], [6], [7] authors have demonstrated the use of different formulations of distance functions for localising robots in both indoor and outdoor environments.…”

“…The localisation strategy proposed is as follows. We use a DF based approach discussed in [5], [6] for representing the map of the environment. This representation is achieved by first obtaining a binary ground plane edge map of the environment and computing its unsigned distance function.…”