Publications

Bayesian Optimization for Fine-Tuning EKF Parameters in UAV Attitude and Heading Reference System Estimation

Published in Aerospace, 2023

Accurately estimating a vehicles 3D motion and seamlessly fusing data from multiple sensors are crucial tasks in various applications. While the Extended Kalman Filter (EKF) reigns supreme in this domain, its effectiveness hinges on optimal tuning of two key parameters: the process and measurement noise covariance matrices (Q and R). Choosing these values correctly can be a daunting challenge, hindering the EKFs full potential. This research tackles this challenge head-on by proposing an EKF innovation consistency statistics-driven Bayesian optimization algorithm. This novel approach automatically tunes Q and R based on the desired performance criteria, specifically, minimizing estimation error through improved measurement innovation consistency. Our extensive results showcase a significant performance boost in the EKF when equipped with the optimized Q and R values obtained through our algorithm. In essence, this research paves the way for easier and more effective utilization of the EKF in various vehicle motion estimation and sensor fusion applications.

Recommended citation: Wondosen, A.; Debele, Y.; Kim, S.-K.; Shi, H.-Y.; Endale, B.; Kang, B.-S. Bayesian Optimization for Fine-Tuning EKF Parameters in UAV Attitude and Heading Reference System Estimation. Aerospace 2023, 10, 1023. https://doi.org/10.3390/aerospace10121023 https://doi.org/10.3390/aerospace10121023

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

Published in Drones, 2023

AI-powered drones fly smarter: This research uses deep learning to detect and pinpoint faulty rotors in drones with multiple motors, making them safer and more reliable. The system can identify problems with 99% accuracy and even works in real-time during flight.

Recommended citation: Debele, Y.; Shi, H.-Y.; Wondosen, A.; Ku, T.-W.; Kang, B.-S. Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs. Drones 2023, 7, 437. https://doi.org/10.3390/drones7070437 https://doi.org/10.3390/drones7070437

Multirotor Unmanned Aerial Vehicle Configuration Optimization Approach for Development of Actuator Fault-Tolerant Structure

Published in Applied Sciences, 2022

Drones designed for safety: This study optimizes multirotor drone design to tolerate actuator failures, ensuring safe operation even when one motor malfunctions. By analyzing achievable forces and moments, the framework adjusts drone parameters to maintain performance and complete missions even with unexpected issues.

Recommended citation: Debele, Y.; Shi, H.-Y.; Wondosen, A.; Kim, J.-H.; Kang, B.-S. Multirotor Unmanned Aerial Vehicle Configuration Optimization Approach for Development of Actuator Fault-Tolerant Structure. Appl. Sci. 2022, 12, 6781. https://doi.org/10.3390/app12136781 https://doi.org/10.3390/app12136781

Improved attitude and heading accuracy with double quaternion parameters estimation and magnetic disturbance rejection

Published in Sensors, 2021

Despite the boom in UAV applications, cheap MEMS sensors pose a challenge: their data is easily corrupted by noise, leading to inaccurate orientation estimates. This study tackles this issue by proposing a novel EKF method with double quaternion parameters, effectively decoupling the magnetometer from attitude calculations. An online error tuning system further combats magnetic noise. Tests reveal the methods superiority over traditional EKF approaches, paving the way for more robust UAV navigation.

Recommended citation: Wondosen, A.; Jeong, J.-S.; Kim, S.-K.; Debele, Y.; Kang, B.-S. Improved Attitude and Heading Accuracy with Double Quaternion Parameters Estimation and Magnetic Disturbance Rejection. Sensors 2021, 21, 5475. https://doi.org/10.3390/s21165475 https://doi.org/10.3390/s21165475

Machine learning approach to real-time 3D path planning for autonomous navigation of unmanned aerial vehicle

Published in Applied Sciences, 2021

Civilian drones are taking flight! From package delivery to first responders, UAVs are poised to revolutionize urban life. But navigating the concrete jungle safely requires AI-powered obstacle avoidance. This research proposes a real-time 3D path planner that helps drones navigate like humanoids, detecting and skirting obstacles in their path.

Recommended citation: Tullu, A.; Endale, B.; Wondosen, A.; Hwang, H.-Y. Machine Learning Approach to Real-Time 3D Path Planning for Autonomous Navigation of Unmanned Aerial Vehicle. Appl. Sci. 2021, 11, 4706. https://doi.org/10.3390/app11104706 https://doi.org/10.3390/app11104706