Open Access

ARTICLE

Deep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures

by Fawad Salam Khan^1,4, Mohd Norzali Haji Mohd^1,*, Saiful Azrin B. M. Zulkifli², Ghulam E Mustafa Abro², Suhail Kazi³, Dur Muhammad Soomro¹

1 Faculty of Electrical and Electronics (FKEE), Universiti Tun Hussein Onn Malaysia, Parit Raja, 81756, Malaysia
2 Department of Electrical & Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Malaysia
3 Faculty of Engineering Science and Technology, Isra University, Hyderabad, 71000, Pakistan
4 Department of Innovation, CONVSYS (Pvt) Ltd., 44000, Islamabad, Pakistan

* Corresponding Author: Mohd Norzali Haji Mohd. Email:

Computers, Materials & Continua 2022, 72(3), 5741-5759. https://doi.org/10.32604/cmc.2022.024927

Received 04 November 2021; Accepted 19 January 2022; Issue published 21 April 2022

Abstract

The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades. Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle (UAV) required maximum accuracy. In this paper, we designed a hybrid framework, which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures. The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient (DDPG) to receive the best reward and take actions according to 3D hand gestures input. The UAV consist of a Jetson Nano embedded testbed, Global Positioning System (GPS) sensor module, and Intel depth camera. The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function. The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives (PID) flight controller. There are six reward functions estimated for 2500, 5000, 7500, and 10000 episodes of training, which have been normalized between 0 to −4000. The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value. The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.

---

Keywords

---