Traditional Global Navigation Satellite Systems (GNSS) experience their limitations in urban canyons. However, it is significant to improve the accuracy of positioning with the rapid development of smart cities. To solve this problem, a UGV-UAV robust cooperative positioning algorithm with object detection is proposed, which utilises an unmanned aerial vehicle (UAV) to assist an unmanned ground vehicle (UGV) to achieve accurate positioning. When the UAV is in the sky with a good reception of satellite signals, the UGV uses the YOLOv3 object detection method to detect the UAV in images captured by camera, and acquires visual measurements including angles and ranges of the ground camera relative to the UAV through the proposed monocular vision measuring with object detection (ODMVM) model. Then, in order to solve the problem that visual measurement is disturbed by the real world, a robust Kalman filter is introduced that integrates measurements from available GNSS, inertial measurement unit (IMU), monocular camera, and the position broadcast of cooperative UAV to obtain more robust and accurate position estimation. Experimental and simulation results show that the proposed cooperation positioning algorithm can improve the positioning accuracy by 73.63% compared with the traditional cooperation positioning algorithm in urban canyons.
Visual inertial odometry (VIO) would have an estimation drift problem in the process of long trajectory for indoor localization, especially in the absence of loop detection or in unknown complex scenes. To solve this problem, a low drift visual inertial odometry with ultra‐wideband (UWB) aided for indoor localization was proposed. Firstly, a single UWB anchor was dropped in an unknown position, and a cost function was formed by the position information output by VIO and the UWB ranging information to obtain the position of the anchor. Then, the single anchor position and the UWB ranging constraints were added to the tightly coupled visual inertial fusion algorithm framework, thereby improving the robustness of motion tracking and reducing the drift of the odometry. Finally, the effectiveness of the proposed method was verified in the actual indoor environment, and the experiment results demonstrated that, compared with state‐of‐the‐art localization methods, the positioning accuracy and robustness were improved significantly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.