ininflueDeveloping Aerial Unmanned Effective Decision Makers
DOI:
https://doi.org/10.51408/1963-0092Keywords:
Object detection, Decision making, Combinatorial problems, Expert knowledgeAbstract
Unmanned aerial vehicles (UAVs, drones) and similar unmanned units are becoming more and more involved in various spheres, such as agriculture, emergency situations, battles, etc. however, in decision making there are still a lot they can be improved to avoid human direct involvement in those problems.To advance in the problem we develop tools to make UAV autonomously effective decision makers, particularly, able to analyze properly given situations and then according to assigned goals select appropriate strategies to achieve the goals.
In the following work we aim to provide a solution for a single UAV which is able to discover units of interest, and select the target to track, manipulate or hit based on expert specified knowledge, as well as discuss further steps.
References
E. Pogossian, A. Javadyan and E. Ivanyan., "Effective discovery of intrusion protection strategies" The International Workshop on Agents and Data Mining, Lecture Notes in Computer Science, St. Petersburg, Russia, pp. 263-274, 2005.
S. Grigoryan, Research and Development of Algorithms and Programs of Knowledge Acquisition and Their Effective Application to Resistance Problems, PhD, Yerevan, Armenia, 2016.
S. Grigoryan, “On validity of personalized planning and integrated testing algorithms in reproducible games”, Proceedings of International Conference in Computer Sciences and Information Technologies, Yerevan, Armenia, pp. 317-321, 2015.
N. Hakobyan, “A system for transforming images to symbolic presentation for combinatorial defense and competition problems”, ISSN 0002-306X. Proc. of the RA NAS and NPUA Ser. of tech. sc., . vol. 72, no. 2, pp. 199-209, 2019.
E. Pogossian, “Effectiveness enhancing knowledge-based strategies for SSRGT class of defense problems”, NATO ASI 2011 Prediction and Recognition of Piracy Efforts Using Collaborative Human-Centric Information Systems, Salamanca, Spain, 2011.
D. Dionne, E. Pogossian, A. Grigoryan, J. Couture and E. Shahbazian, “An optimal sequential optimization approach in application to dynamic weapon allocation in naval warfare”, 11th International Fusion 2008 Conference in Cologne, July 1-3, 2008.
E. Pogossian, D. Dionne, A. Grigoryan, J. Couture and E. Shahbazian, “Developing goals directed search models empowering strategies against single ownship air threats”, CSIT2009: International Conference in Computer Sciences and Information Technologies, Yerevan, Armenia, 5 p. 2009.
E. Pogossian, “Towards adequate constructive models of mental systems”, CSIT2017: International Conference in Computer Science and Information Technologies, Yerevan, Armenia, pp. 96-101, 2017.
E. Pogossian, Constructing Models of Being by Cognizing, Academy of Sciences of Yerevan, Armenia, 2020.
M. Buniatyan, Developing Software for Expert Knowledge/Classifiers-Based Effective Strategies Formation and Applications, Master thesis, IIAP NAS RA, Yerevan, Armenia, 2022.
F. Li, S. Li, C. Zhu, X. Lan and H. Chang, “Cost-effective class-imbalance aware CNN for vehicle localization and categorization in high resolution aerial images”, Remote Sensing, vol 9, no. 5, pp. 1-29, 2017.
K. Zhang, Ch. Wang, X. Yu, et al. “Research on mine vehicle tracking and detection technology based on YOLOv5”, Systems Science and Control Engineering, vol. 10, no. 1, pp. 347-366, 2022.
YOLOv5 repository [Online] Available: https://github.com/ultralytics/yolov5
N. Sabina, M. Aneesa and P. Haseena, “Object detection using YOLO and mobilenet SSD: A comparative study”, Internetional Journal of Engineering Research&Technology, vol. 11, no. 6, 134-138, 2022.
K. R. Ahmed and P. Smart, “Detection using deep learning based on dilated convolution”, Sensors, 21, 24, 8406, 2021. Doi: 10.3390/s21248406
A. Bochkovskiy, Ch. Wang and M. Liao, “YOLOv4: Optimal speed and accuracy of object detection”. arXiv:2004.10934v1, 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Sedrak V. Grigoryan and Edward M. Pogossian
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
