Aerial Intruder Interception Based on Threat Classification for Enhanced Situational Awareness

Eshaan Khanapuri, Anusna Chakraborty, Ross Thayer, Jayanth Ammapalli, Jiarui Liu, Szu Wei Lin, and Joseph Yadegar

Peer Reviewed

Abstract:	Intent classification of Unmanned Aerial Vehicles (UAVs) either as a standalone vehicle or in swarm is extremely important in the current world. With the rise in autonomy of these platforms, there have been several instances where UAVs have, instead of providing benefit, been a nuisance and created chaos and confusion. Activity classification for threat assessment of UAVs is a relatively new area where different types of machine learning models are been tested. In this paper, the authors have provided a methodology to passively perform intent classification and a comparative study of different classification models namely Hidden Markov Model (HMM), Convolutional Neural Network - Long Short Term Memory (CNN-LSTM), Gramian Angular fields (GAF) with CNN and Transformers have been performed for action classification for threat identification. Additionally, the authors have developed a simulator using ROS and Gazebo to deploy these models in simulation along with a resource allocation and target interception framework to demonstrate an actionable and intelligent as well as automated Counter-UAS system. Index Terms—intent classification, threat identification, Counter-UAS, CNN, LSTM, GAF, Transformers, PN-guidance, Voronoi Diagrams
Published in:	2025 IEEE/ION Position, Location and Navigation Symposium (PLANS) April 28 - 1, 2025 Salt Lake Marriott Downtown at City Creek Salt Lake City, UT
Pages:	1488 - 1499
Cite this article:	Khanapuri, Eshaan, Chakraborty, Anusna, Thayer, Ross, Ammapalli, Jayanth, Liu, Jiarui, Lin, Szu Wei, Yadegar, Joseph, "Aerial Intruder Interception Based on Threat Classification for Enhanced Situational Awareness," 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Salt Lake City, UT, April 2025, pp. 1488-1499.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In