Fuzzy Systems and its Applications

Fuzzy Systems and its Applications

Designing an Intelligent Pathfinder Drone with Deep Learning and Fuzzy Logic

Document Type : Original Article

Authors
فریبرز مولایی 1
Abdolmajd Mousavi 2
Mohamad Bagher Dowlatshahi 1
1 Faculty of Engineering and Technology, Lorestan University, Khorramabad, Iran
2 ّFaculty of Engineering and Technology, Lorestan University, Khorramabad, Iran
10.22034/jfsa.2024.454778.1203
Abstract
Drones are flying robots that have the ability to fly unmanned with different structures and can benefit from intelligence to make appropriate decisions in new situations. Also, with the progress of artificial intelligence (AI) in recent years, its application can be seen in most other branches. This paper presents an intelligent drone that is able to maneuver correctly while flying on roads. For this purpose, a deep learning network (Network Learning Deep) has been used, for its training, a large data set of nature images and urban roads has been collected, and Fuzzy Logic is used to obtain the best angle and speed that Keeps drone on track, used. The fuzzy logic system acts as an interface layer between the deep learning component and the UAV flight control system. This system corrects the flight path and speed control based on the real-time sensor data and the output of the deep learning network. The accuracy of the deep learning network used in this article is improved compared to the accuracy of the deep learning networks used in similar cases. The goal is to improve the accuracy of learning by expanding the dataset and network compared to previous works and reduce the complexity by using fuzzy logic. The designed system was implemented on a hexacopter and was investigated on the roads outside the city and at low altitude. This accuracy is equal to 93.18%, which indicated its acceptable performance. However, it is possible to use distance sensors around the drone or stereo cameras on the drone to increase accuracy and help make better fuzzy logic decisions.
Keywords
UAV
Deep Neural Network
Fuzzy Logic
autonomous flight
Pathfinder Drone
Subjects
[2]    Ahmed, T., Rahman, T., Roy, B. B., & Uddin, J. (2021). Drone Detection by Neural Network Using GLCM and SURF. Journal of Information Systems and Telecommunication, 9(33), 15-24.
[3]    Al-Sharman, M. K., Zweiri, Y., Jaradat, M. A. K., Al-Husari, R., Gan, D., & Seneviratne, L. D. (2019). Deep-learning-based neural network training for state estimation enhancement: Application to attitude estimation. IEEE Transactions on Instrumentation and Measurement, 69(1), 24-34.
 
[4]    Bezas, K., Tsoumanis, G., Angelis, C. T., & Oikonomou, K. (2022). Coverage path planning and point-of-interest detection using autonomous drone swarms. Sensors, 22(19), 7551.
[5]    Brownlee, J. (2019). How to configure image data augmentation in Keras. Machine Learning Mastery, 5.
[6]    Chamayou, G. (2015). A Theory of the Drone. New Press, The.
[7]    Chen, Q., Chen, J., & Huang, W. (2022). Pathfinding method for an indoor drone based on a BIM- semantic model. Advanced Engineering Informatics, 53, 101686.
[8]    Diller, J., & Han, Q. (2023). Energy-Aware Drone Path Finding with a Fixed-Trajectory Ground Vehicle.
[9]    Dorrani, Z., Farsi, H., & Mohammadzadeh, S. (2022). Edge detection and identification using deep learning to identify vehicles. Journal of Information Systems and Telecommunication (JIST), 3(39), 201.
[10]        Do, T., Carrillo-Arce, L. C., & Roumeliotis, S. I. (2019). High-speed autonomous quadrotor navigation through visual and inertial paths. The International Journal of Robotics Research, 38(4), 486-504.
[11]    ermaugan, U., Yildiz, B., & Salman, F. S. (2022). A learning based algorithm for drone routing. Computers & Operations Research, 137, 105524.
[12]    Giusti, A., Guzzi, J., Ciresan, D. C., He, F. L., Rodriguez, J. P., Fontana, F., ... & Gambardella, L.M. (2015). A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robotics and Automation Letters, 1(2), 661-667.
[13]        Hafez-Kolahi, H., & Kasaei, S. (2019). Information bottleneck and its applications in deep learning. arXiv preprint arXiv:1904.03743.
[14]        Jindal, K., & Aron, R. (2022). A hybrid machine learning approach for sentiment analysis of beauty products reviews. Journal of Information Systems and Telecommunication (JIST), 1(37), 1.
[15]        Jung, S., Hwang, S., Shin, H., & Shim, D. H. (2018). Perception, guidance, and navigation for indoor autonomous drone racing using deep learning. IEEE Robotics and Automation Letters, 3(3), 2539-2544.
[16]        Kim, D. K., & Chen, T. (2015). Deep neural network for real-time autonomous indoor navigation. arXiv preprint arXiv:1511.04668.
[17]        Kulkarni, P. V., Rai, S., Sachdeo, R., & Kale, R. (2023). Deep Learning-based Educational User Profile and User Rating Recommendation System for E-Learning. Journal of Information Systems and Telecommunication (JIST), 3(43), 185.
[18]        Kilic, K. I., & Mostarda, L. (2021). Heuristic drone pathfinding over optimized charging station grid. IEEE Access, 9, 164070-164089.
 
[19]        MJ, C. M. B. (2023). Convolutional Neural Networks for Medical Image Segmentation and Classification: A Review. Journal of Information Systems and Telecommunication (JIST), 4(44), 347.
[20]        Mozaffari, F., Raeesi Vanani, I., Mahmoudian, P., & Sohrabi, B. (2023). Application of Machine Learning in the Telecommunications Industry: Partial Churn Prediction by using a Hybrid Feature Selection Approach. Journal of Information Systems and Telecommunication (JIST), 4(44), 331.
[21]    Ricco, J. (2017). What is max pooling in convolutional neural networks.
[22]        Resendiz, V. M. A., & Rivas-Araiza, E. A. (2016). System Identification of a Quad-rotor in X Con- figuration from Experimental Data. Res. Comput. Sci., 118, 77-86.
[23]        Sanchez-Lopez, J. L., Sampedro, C., Cazzato, D., & Voos, H. (2019, June). Deep learning based semantic situation awareness system for multirotor aerial robots using LIDAR. In 2019 International Conference on Unmanned Aircraft Systems (ICUAS) (pp. 899-908). IEEE.
[24]        Sandooghdar, A., & Yaghmaee, F. (2022). Deep learning approach for cardiac MRI images. Journal of Information Systems and Telecommunication (JIST), 1(37), 61.
[25]        Schedl, D. C., Kurmi, I., & Bimber, O. (2021). An autonomous drone for search and rescue in forests using airborne optical sectioning. Science Robotics, 6(55), eabg1188.
[26]        Santana, P., Correia, L., Mendon;:a, R., Alves, N., & Barata, J. (2013). Tracking natural trails with swarm-based visual saliency. Journal of Field Robotics, 30(1), 64-86.
[27]    Tch, A. (2017). The mostly complete chart of Neural Networks, explained. Online Medium.
[28]    Vo, A. (2018). Deep Learning-Computer Vision and Convolutional Neural Networks,".
[29]    Yiu, T. (2019). Understanding neural networks. Towards Data Science, 2.
[30]    Zadeh, L. A. (1965), Fuzzy sets. Information and Control, 
Fuzzy Systems and its Applications
Volume 7, Issue 1 - Serial Number 14
Open Access Statement
June 2024
Pages 189-207

  • Receive Date 29 April 2024
  • Revise Date 16 August 2024
  • Accept Date 11 September 2024