CARG AI4UAV: AI-based Counter UAS Systems

Rapid advancements in UAV technology demand sophisticated detection and response systems to address threats in national defense, security, and airspace safety. The CARG AI4UAV team utilizes their expertise in radar, statistical signal processing, machine learning, and computer vision to develop systems capable of detecting, classifying, and tracking UAVs using both ground and airborne sensors.

Key aspects of our research include the development of resilient AI systems that maintain reliability despite domain shifts and uncertainties. The system architecture integrates ground sensors like radar and PTZ cameras with interceptor UAVs to provide early warning, detection, tracking, and payload classification. The team tackles challenges such as long-distance object detection, ensuring model robustness with unseen data, and multi-sensor fusion. Our work combines modeling and simulations with extensive data collection. This work is supported by funding from NRC and NSERC.

Publications

2026-04-25

Conferences

TRUST: Trajectory-guided State-Space Temporal Test-Time Adaptation

Published in ICLR, Catch, Adapt, and Operate: Monitoring ML Models Under Drift Workshop

by F. Dadboud, H. Azad, M. Bolic, I. Mantegh,

TRUST is a backpropagation-free Bayesian test-time adaptation method for vision-language video object detection that improves robustness to gradual temporal distribution shifts by combining a global cache and scale statistics with trajectory-guided instance-level state-space filtering.

Download Paper

2025-09-18

Conferences

AI-Enabled Radar and Camera Integration for Real-Time Drone Detection and Classification

Published in 44th Digital Avionics Systems Conference

by V. Mehta, H. Azad, F. Dadboud, M. Bolic, I. Mantegh

A real-time AI framework is shown that fuses radar and camera sensors on edge devices to detect, track, and classify drones. Extensive day/night field trials, with synchronized radar tracks and RGB/IR video, demonstrate robust performance.

2025-09-18

Conferences

CycleGAN-Assisted Domain Adaptation for UAV Payload Detection

Published in 44th Digital Avionics Systems Conference

by H. Azad, M. Bolic and I. Mantegh

The paper targets vision-based detection of UAVs carrying payloads. To address the synthetic→real domain gap, it utilizes CycleGAN to translate real test images into a synthetic style, and then classifies them using pre-trained ResNet/EfficientNet models in a two-stage pipeline.

2025-04-14

Conferences

Synthesized Control for In-field UAV Moving Target Interception via Deep Reinforcement Learning and Fuzzy Logic

Published in ICUAS 2025

by Bingze Xia, Mohammad Ahsan Akhlaque, Iraj Mantegh, Miodrag Bolic, Wenfang Xie

This paper develops AI-based multi-UAV interception algorithm through simulation and validating the system through real-world drone tests in dynamic environments.

Download Paper

2025-02-28

Conferences

DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains

Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

by F. Dadboud, H. Azad, V. Mehta, M. Bolic, I. Mantegh

This paper is about studying drone detection under different types of domain shift.

Download Paper

2024-12-15

Reports

UAV Object Tracking with Modular Architecture

Published in University of Ottawa

by Nathaniel Bowness

Signal processing and machine learning for fusion of airborne camera and radar data.

2024-01-01

Manuscripts

An Intent Modeling and Inference Framework for Autonomous and Remotely Piloted Aerial Systems

Published in arXiv preprint arXiv:2409.08472

by Kaza, K, Mehta, V, Azad, H, Bolic, M, Mantegh, I

An Intent Modeling and Inference Framework for Autonomous and Remotely Piloted Aerial Systems published in arXiv preprint arXiv:2409.08472.

Download Paper

2023-10-01

Conferences

Air-to-Air Simulated Drone Dataset for AI-powered problems

Published in 2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC)

by Azad, H, Mehta, V, Dadboud, F, Bolic, M, Mantegh, I

This paper presents a comprehensive multi-view air-to-air simulated vision drone dataset.

Download Paper

2023-05-18

Conferences

Simulated Dataset for the Loaded vs. Unloaded UAV Classification Problem Using Deep Learning

Published in 2023 IEEE Sensors Applications Symposium (SAS)

by Azad, H, Mehta, V, Bolic, M, Mantegh, I

This paper introduces the first published vision dataset for the loaded vs. unloaded UAV classification problem.

Download Paper

2023-01-01

Conferences

A Hybrid Framework for Object Distance Estimation using a Monocular Camera

Published in 2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC)

by Patel, V, Mehta, V, Bolic, M, Mantegh.

A deep learning method for estimating the distance of intruder UAVs using a single camera.

Download Paper

2023-01-01

Conferences

A Deep Learning Approach for Drone Detection and Classification Using Radar and Camera Sensor Fusion

Published in 2023 IEEE Sensors Applications Symposium (SAS)

by Mehta, V, Dadboud, F, Bolic, M, Mantegh, I

A Deep Learning Approach for Drone Detection and Classification Using Radar and Camera Sensor Fusion published in 2023 IEEE Sensors Applications Symposium (SAS).

Download Paper

2023-01-01

Conferences

Real-Time UAV and Payload Detection and Classification System Using Radar and Camera Sensor Fusion

Published in 2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC)

by Mehta, V, Azad, H, Dadboud, F, Bolic, M, Mantegh, I

Real-Time UAV and Payload Detection and Classification System Using Radar and Camera Sensor Fusion published in 2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC).

Download Paper

2021-01-01

Conferences

Single-Stage UAV Detection and Classification with YOLOV5: Mosaic Data Augmentation and PANet

Published in 2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

by Dadboud, F., Patel, V., Mehta, V., Bolic, M., Mantegh, I.

This paper is about studying drone detection under different types of domain shift.

Download Paper

2021-01-01

Conferences

Tracking and Classification of Drones and Birds at a Far Distance Using Radar Data

Published in N/A

by Mehta, V., Bolic, M., Mantegh, I., Vidal, C.

Distinguishing between birds and drones based on their motion patterns.

Download Paper

2020-10-01

Conferences

Hybrid AI-enabled Method for UAS and Bird Detection and Classification

Published in IEEE International Conference on Systems, Man, and Cybernetics (SMC)

by X. Zhang, V. Mehta, M. Bolic and I. Mantegh

A novel approach combining IMM filters and LSTM-based RNNs achieved 99.3% accuracy in classifying drones versus birds using synthetic trajectory data.

Researchers

Miodrag Bolic
Principal Investigator

Fardad Dadboud
Graduate Student

Dr. Hamid Azad
Research Staff

Varun_mehta
Collaborators

Academic Collaborators

Researcher Name	University/Institute	Position
I. Mantegh	NRC, Canada	Technology and Team Lead- AI Aerial Robotics & Counter UAS

Industrial Partners

Company Name	Location
National Research Council Canada (NRC)	Ottawa, Canada

CARG AI4UAV: AI-based Counter UAS Systems

Publications

TRUST: Trajectory-guided State-Space Temporal Test-Time Adaptation

AI-Enabled Radar and Camera Integration for Real-Time Drone Detection and Classification

CycleGAN-Assisted Domain Adaptation for UAV Payload Detection

Synthesized Control for In-field UAV Moving Target Interception via Deep Reinforcement Learning and Fuzzy Logic

DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains

UAV Object Tracking with Modular Architecture

An Intent Modeling and Inference Framework for Autonomous and Remotely Piloted Aerial Systems

Air-to-Air Simulated Drone Dataset for AI-powered problems

Simulated Dataset for the Loaded vs. Unloaded UAV Classification Problem Using Deep Learning

A Hybrid Framework for Object Distance Estimation using a Monocular Camera

A Deep Learning Approach for Drone Detection and Classification Using Radar and Camera Sensor Fusion

Real-Time UAV and Payload Detection and Classification System Using Radar and Camera Sensor Fusion

Single-Stage UAV Detection and Classification with YOLOV5: Mosaic Data Augmentation and PANet

Tracking and Classification of Drones and Birds at a Far Distance Using Radar Data

Hybrid AI-enabled Method for UAS and Bird Detection and Classification

Researchers

Miodrag Bolic

Fardad Dadboud

Dr. Hamid Azad

Varun_mehta

Academic Collaborators

Industrial Partners