Inspection of Pole-Like Structures Using a Visual-Inertial Aided VTOL Platform with Shared Autonomy

Abstract

This paper presents an algorithm and a system for vertical infrastructure inspection using a vertical take-off and landing (VTOL) unmanned aerial vehicle and shared autonomy. Inspecting vertical structures such as light and power distribution poles is a difficult task that is time-consuming, dangerous and expensive. Recently, micro VTOL platforms (i.e., quad-, hexa- and octa-rotors) have been rapidly gaining interest in research, military and even public domains. The unmanned, low-cost and VTOL properties of these platforms make them ideal for situations where inspection would otherwise be time-consuming and/or hazardous to humans. There are, however, challenges involved with developing such an inspection system, for example flying in close proximity to a target while maintaining a fixed stand-off distance from it, being immune to wind gusts and exchanging useful information with the remote user. To overcome these challenges, we require accurate and high-update rate state estimation and high performance controllers to be implemented onboard the vehicle. Ease of control and a live video feed are required for the human operator. We demonstrate a VTOL platform that can operate at close-quarters, whilst maintaining a safe stand-off distance and rejecting environmental disturbances. Two approaches are presented: Position-Based Visual Servoing (PBVS) using an Extended Kalman Filter (EKF) and estimator-free Image-Based Visual Servoing (IBVS). Both use monocular visual, inertia, and sonar data, allowing the approaches to be applied for indoor or GPS-impaired environments. We extensively compare the performances of PBVS and IBVS in terms of accuracy, robustness and computational costs. Results from simulations and indoor/outdoor (day and night) flight experiments demonstrate the system is able to successfully inspect and circumnavigate a vertical pole.

Interlinked Visual Tracking and Robotic Manipulation of Articulated Objects

“…Indeed, the VVS estimation depends on the number of the f tracked lines and their relative position. For example, to correctly estimate the FB pose, a minimal set of 3 noncoplanar lines is required to ensure that the stacked image Jacobian, and consequently the articulation matrix, is full rank (the same problem is remarked in the dual context of VS [19]). The lines coplanarity can be detected with additional computation.…”

“…where the dot over the variables denotes the time derivative, J i is the 6 × m Jacobian of the object link where the i-th line is defined (details are given in the Appendix), and L i is the 2 × 6 image Jacobian associated to the i-th line [19]:…”

Towards an Autonomous Vision-Based Unmanned Aerial System against Wildlife Poachers

“…The estimation of the rotation of the UAV is retrieved from the gyroscope of the IMU. The subtraction of the roll and pitch rotations of the UAV from the image estimation is called de-rotation [ 78 , 79 ]. The relevant formulas are presented in Equation ( 17 ).…”

Assisted Control for Semi-Autonomous Power Infrastructure Inspection Using Aerial Vehicles

“…Passively, the assistance is performed by directing the pilot using external forces through a haptic control device as demonstrated in [5], [6], [7]. Whereas the active approach works by altering the direction and magnitude of the operators input velocity [8], usually to ensure collision free motion when operating in close proximity to obstacles (e.g power infrastructure in the case of this work). Typically, the motivation behind this is so that the UAV maintains smooth and continuous motion during operation leading to improved data collection.…”