Vision Navigation System to Manoeuvre Unmanned Aerial Vehicle (UAV)
Title: Vision Navigation System to Manoeuvre Unmanned Aerial Vehicle (UAV)
Authors: Patrick T. Saleh (Centre for Automation and Robotics Research, Sheffield Hallam University); Jacques Penders (Centre for Automation and Robotics Research, Sheffield Hallam University); Lyuba Alboul (Centre for Automation and Robotics Research, Sheffield Hallam University);
Year: 2020
Citation: Saleh, P. T., Penders, J., Alboul, L., (2020). Vision Navigation System to Manoeuvre Unmanned Aerial Vehicle (UAV). UKRAS20 Conference: “Robots into the real world” Proceedings, 142-144. doi: 10.31256/Jb6Qv4S
Abstract:
This paper describes the development and the implementation of an omnidirectional multiple stereo cameras vision system. The vision system is compact and light enough to operate on board a commercially available off the shelf miniature UAV (Unmanned Aerial Vehicle)-Quadrotor. The vision system contains several stereo cameras ruggedly fixed on- board the UAV-Quadrotor, it is oriented in such a way that it has a 360 degrees omnidirectional visual coverage. The paper demonstrates that by combining several stereo cameras, it can provide and combine depth information and optical flow data in real time to an on-board image processing computer. One can estimate the position and the orientation such as roll, pitch and yaw of the UAV in 3D (three dimensions) space accurately without the aid of GPS (Global Positing System), IMU (Initial Measurement Unit) or any other external navigation or orientation aid. This method can be described as “Simultaneous Localization and Exploration Oriented Visual Navigation”. It is a development of a vision system capable of navigating autonomously an UAV-Quadrotor through random free spaces within an unknown complex environment and without any mapping, it simply performs by detecting and avoiding obstacles calculating the required “through flight path”.