Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs.

In-flight system failure is one of the major safety concerns in the operation of unmanned aerial vehicles (UAVs) in urban environments. To address this concern, a safety framework consisting of following three main tasks can be utilized: (1) Monitoring health of the UAV and detecting failures, (2) Finding potential safe landing spots in case a critical failure is detected in step 1, and (3) Steering the UAV to a safe landing spot found in step 2. In this paper, we specifically look at the second task, where we investigate the feasibility of utilizing object detection methods to spot safe landing spots in case the UAV suffers an in-flight failure. Particularly, we investigate different versions of the YOLO objection detection method and compare their performances for the specific application of detecting a safe landing location for a UAV that has suffered an in-flight failure. We compare the performance of YOLOv3, YOLOv4, and YOLOv5l while training them by a large aerial image dataset called DOTA in a Personal Computer (PC) and also a Companion Computer (CC). We plan to use the chosen algorithm on a CC that can be attached to a UAV, and the PC is used to verify the trends that we see between the algorithms on the CC. We confirm the feasibility of utilizing these algorithms for effective emergency landing spot detection and report their accuracy and speed for that specific application. Our investigation also shows that the YOLOv5l algorithm outperforms YOLOv4 and YOLOv3 in terms of accuracy of detection while maintaining a slightly slower inference speed.

Failure Detection in Quadcopter UAVs Using K-Means Clustering.

We propose an unmanned aerial vehicle (UAV) failure detection system as the first step of a three-step autonomous emergency landing safety framework for UAVs. We showed the effectiveness and feasibility of using vibration data with the k-means clustering algorithm in detecting mid-flight UAV failures for that purpose. Specifically, we measured vibration signals for different faulty propeller cases during several test flights, utilizing a custom-made hardware system. After we made the vibration graphs and extracted the data, we investigated to determine the combination of acceleration and gyroscope parameters that results in the best accuracy of failure detection in quadcopter UAVs. Our investigations show that considering the gyroscope parameter in the vertical direction (gZ) along with the accelerometer parameter in the same direction (aZ) results in the highest accuracy of failure detection for the purpose of emergency landing of faulty UAVs, while ensuring a quick detection and timely engagement of the safety framework. Based on the parameter set (gZ-aZ), we then created scatter plots and confusion matrices, and applied the k-means clustering algorithm to the vibration dataset to classify the data into three health state clusters-normal, faulty, and failure. We confirm the effectiveness of the proposed system with flight experiments, in which we were able to detect faults and failures utilizing the aforementioned clusters in real time.