Abstract-This paper proposes an image-based localization method that enables to estimate a bounded domain of the pose of an unmanned aerial vehicle (UAV) from uncertain measurements of known landmarks in the image. The approach computes a domain that should contain the actual robot pose, assuming bounded image measurement errors and landmark position uncertainty. It relies on interval analysis and constraint propagation techniques to rigorously back-propagate the errors through the non-linear observation model. Attitude information from onboard sensors is merged with image observations to reduce the pose uncertainty domain, along with prediction based on velocity measurements. As tracking landmarks in the image is prone to errors, the proposed method also enable fault detection from measurement inconsistencies. This method is tested using a quadcopter UAV with an onboard camera.

An interval-based approach to cooperative localization for a group of unmanned aerial vehicles (UAVs) is proposed. It computes a pose uncertainty domain for each robot, i.e., a set that contains the true robot pose, assuming bounded error measurements. The algorithm combines distances measurements to the ground station and between UAVs, with the tracking of known landmarks in camera images, and provides a guaranteed enclosure of the robots pose domains. Pose uncertainty domains are computed using interval constraint propagation techniques, thanks to a branch and bound algorithm. We show that the proposed method also provides a good point estimate, that can be further refined using nonlinear iterative weighted least squares. Results are presented for simulated two-robots configurations, for experimental data, and compared with a classical Extended Kalman Filter.

Abstract-This paper presents a global behavioral architecture used as a coordinator for the global navigation of an autonomous vehicle in an urban context including traffic laws and other features. As an extension to our previous work, the approach presented here focuses on how this manager uses perceived information (from low cost cameras and laser scanners) combined with digital road-map data to take decisions. This decision consists in retrieving the car's state regarding the global navigation goal, selecting which local navigation task should be executed (either lane following or intersection maneuvers), providing some round constraints and further defining the reference trajectory to be met by the selected local task. This system was experimented in a real autonomous car and provided satisfactory results.