Autonomous Sensor-based Control of Aerial Manipulator for Horizontal Pipe Structure Tracking with Continuous Contact

Continuous health monitoring of industrial pipelines, railway tracks, and powerline-like horizontal structures is crucial for ensuring human safety. Recently, the aerial manipulator concept is getting more attention for the contact inspection of industrial structures. This paper proposed the autonomous vision-based control of an aerial manipulator for tracking of horizontal pipe structure while maintaining continuous contact by a manipulator. The perception module of the proposed approach includes a deep learning technique for pipe identification in the image, a classical vision for feature extraction, and a Kalman filter to resolve the data latency problem in real time. The integration of LIDAR and the camera sensor has been used to extract the cartesian coordinate of the approximate contact point. The manipulator is designed and developed along with inverse kinematics to maintain continuous contact with the pipe. Image-based sliding mode controller is used for lateral and yaw orientation control of the aerial platform. The altitude control is done using a LIDAR sensor. The novel forward velocity function is introduced which serves the purpose of smooth tracking along with maintaining a pipe in the reachable space of the manipulator. The fully autonomous operation strategy has been designed to organize subtasks sequentially with feedback. During the tracking of a pipeline, the lateral position and altitude position with respect to manipulator’s base did not deviate beyond ± 0.2m. Fully autonomous vision-based control of aerial manipulator has been validated experimentally on a 10-meter long pipeine.