PD+SMC Quadrotor Control for Altitude and Crack Recognition Using Deep Learning

Abstract

Building inspection is a vital task because infrastructure damage puts people at risk or causes economic losses. Thanks to the technological breakthroughs in regard to Unmanned Aerial Vehicles (UAVs) and intelligent systems, there is a real possibility to implement an inspection by means of these technologies. UAVs allow reaching difficult places and, depending on the hardware carried onboard, take data or compute algorithms to understand the environment. This paper proposes a real-time robust altitude control strategy for a quadrotor aircraft, also a convolutional neuronal network for crack recognition is developed. The main idea of this proposal is to lay the background for an autonomous system for the inspection of structures using a UAV. For the robust control, a combination of two control actions, one linear (PD) and another nonlinear (Sliding Mode) is used. The combination of these control actions allows increasing the system's performance. To verify the satisfactory performance of proposed control law, simulations and experimental results with a quadrotor, in the presence of disturbances, are presented. For crack recognition in images, several experiments were carried out validating the proposed model. For CNN training, a database of cracks was built from images taken from the Internet.

Multi-Robot Space Exploration: An Augmented Arithmetic Approach

“…This represents a promising approach for subsequent implementation for mobile robotic configuration. J. M. Vazquezs et al [53] presented a robust quadrotor aircraft altitude control strategy in real time, which also develops a convolutionary neural network for crack detection. The principle idea behind their proposal was to lay the foundations of an autonomous UAV structural inspection system.…”

Fast Model-Free Learning for Controlling a Quadrotor UAV With Designed Error Trajectory

“…Once the trajectory reached the sliding surface, the system would switch to the sliding mode. For example, Vazquez-Nicolas et al [16] used SMC to realize robust altitude control. They defined a sliding surface which was the desired altitude error trajectory, and combined SMC with the PD controller to improve the UAV's performance.…”

A Moving Target Tracking Control of Quadrotor UAV Based on Passive Control and Super-Twisting Sliding Mode Control

“…In order to achieve attitude stabilization and position tracking control of the quadrotor, various advanced control techniques have been developed. Many remarkable achievements have been obtained such as robust PID control [11], active disturbance rejection method [12], feedback linearization control [13], backstepping control [14], model predictive control [15], adaptive control [16], immersion and invariance control [17], reinforcement learning [18], and composite stability control [19,20]. Although the above methods can accomplish the autonomous flight of UAVs, some of them still have limited capability to handle uncertainties and external disturbances.…”

“…e whole position tracking system acts as a cascade of the drive system (17) and driven system (20). If the relative velocity and the virtual control input are designed according to (16) and (19), the control strategy can guarantee that the position control system is passive and globally stable at the origin.…”