Noise Tolerant Identification and Tuning Approach Using Deep Neural Networks For Visual Servoing Applications

TL;DR

This paper introduces a noise-tolerant deep neural network-based method for real-time identification and tuning of UAV visual servoing systems, improving robustness against sensor noise and external disturbances.

Contribution

The paper presents DNN-NP-MRFT, a novel approach combining deep neural networks with modified relay feedback test for noise-resilient system identification and tuning in UAV visual servoing.

Findings

DNN-NP-MRFT effectively detects performance changes with high noise levels.

The method accurately predicts system behavior and performance limits.

UAVs tuned with DNN-NP-MRFT can reject external disturbances like wind and human interaction.

Abstract

Vision based control of Unmanned Aerial Vehicles (UAVs) has been adopted by a wide range of applications due to the availability of low-cost on-board sensors and computers. Tuning such systems to work properly requires extensive domain specific experience, which limits the growth of emerging applications. Moreover, obtaining performance limits of UAV based visual servoing is difficult due to the complexity of the models used. In this paper, we propose a novel noise tolerant approach for real-time identification and tuning of visual servoing systems, based on deep neural networks (DNN) classification of system response generated by the modified relay feedback test (MRFT). The proposed method, called DNN with noise protected MRFT (DNN-NP-MRFT), can be used with a multitude of vision sensors and estimation algorithms despite the high levels of sensor's noise. Response of DNN-NP-MRFT to noise perturbations is investigated and its effect on identification and tuning performance is analyzed. The proposed DNN-NP-MRFT is able to detect performance changes due to the use of high latency vision sensors, or due to the integration of inertial measurement unit (IMU) measurements in the UAV states estimation. Experimental identification closely matches simulation results, which can be used to explain system behaviour and predict the closed loop performance limits for a given hardware and software setup. We also demonstrate the ability of DNN-NP-MRFT tuned UAVs to reject external disturbances like wind, or human push and pull. Finally, we discuss the advantages of the proposed DNN-NP-MRFT visual servoing design approach compared with other approaches in literature.