Autonomous tracking and navigation controller for an unmanned aerial vehicle based on visual data for inspection of oil and gas pipelines

摘要

This paper presents automated navigation control of an Unmanned Aerial Vehicle (UAV) based on visual data gathered by onboard camera. With depletion of easy resources and health, safety and environmental (HSE) challenges in exploiting newly found resources in hostile conditions are forcing oil and gas companies to look for robotic solutions for their problems. Pipelines carrying inflammable and toxic petroleum products are one of the most critical component of oil and gas industry. Being laid in extreme environmental conditions these critical assets require continuous inspection and maintenance. An UAV carrying non-contact sensors is proposed to use for external inspection of the visible pipeline sections. Till now UAVs are mostly used for general purpose visual surveillance while flying at very high altitude but in this novel work we propose accurate tracking and inspection while flying at very low altitude in close vicinity of the ground pipeline structure. Proposed automated inspection of the pipelines by the UAV has two stages firstly identification of the pipeline and secondly navigation control of the UAV for tracking of the pipeline structure. Both identification and tracking are based on visual data gathered by onboard cameras without any additional help of GPS information. This novel navigation control mechanism further has double layers of correction loops namely angular and lateral corrections. Navigation control uses heuristically tunes PID controllers and required geometrical parameters for angular and lateral corrections are extracted from visual data generated by onboard video camera.