Due to technological advances in the drone industry, security threats induced by unmanned aerial vehicles (UAVs) are becoming more relevant. Fast and accurate localisation systems need to be designed. One approach is localisation of UAVs by their sound using acoustic techniques. So far, a systematic performance assessment of acoustic techniques for drone localisation, based on real-world data, is lacking. This work presents a comparison of selected techniques using real-world measurement data. The achieved performance serves as a baseline for future design of novel localisation methods. Three techniques are chosen. The first technique estimates the time-difference-of-arrival (TDOA) using generalised cross-correlation with phase transform weighting (GCC-PHAT). The second technique is differential evolution, which approaches the localisation task as a global optimisation problem. The third technique is conventional frequency domain beamforming. Real-world data of 5 quadrotor UAVs were used acquired with an acoustic microphone-array. The performance of the techniques is assessed using the absolute error between the estimated source location and the true source location obtained from the onboard GPS tracker of the drones. GCC-PHAT and differential evolution attempt to estimate the drone position in one or few steps. They have a much shorter runtime than beamforming, which is an exhaustive grid search algorithm. However, these techniques result in lower detection ranges and accuracy compared to beamforming.@en

Threats posed by drones urge defence sectors worldwide to develop drone detection systems. Visible-light and infrared cameras complement other sensors in detecting and identifying drones. Application of Convolutional Neural Networks (CNNs), such as the You Only Look Once (YOLO) algorithm, are known to help detect drones in video footage captured by the cameras quickly, and to robustly differentiate drones from other flying objects such as birds, thus avoiding false positives. However, using still video frames for training the CNN may lead to low drone-background contrast when it is flying in front of clutter, and omission of useful temporal data such as the flight trajectory. This deteriorates the drone detection performance, especially when the distance to the target increases. This work proposes to pre-process the video frames using a Bio-Inspired Vision (BIV) model of insects, and to concatenate the pre-processed video frame with the still frame as input for the CNN. The BIV model uses information from preceding frames to enhance the moving target-to-background contrast and embody the target’s recent trajectory in the input frames. An open benchmark dataset containing infrared videos of small drones (< 25 kg) and other flying objects is used to train and test the proposed methodology. Results show that, at a high sensor-to-target distance, the YOLO algorithms trained on BIV-processed frames and concatenation of the BIV-processed frames with still frames increase the Average Precision (AP) to 0.92 and 0.88, respectively, compared to 0.83 when it is trained on still frames alone.@en

Loss of control (LOC) is a prevalent cause of drone crashes. Onboard prevention systems should be designed requiring low computing power, for which data-driven techniques provide a promising solution. This study proposes the use of recurrent neural networks (RNNs) for LOC prediction. Four architectures were trained in order to identify which RNN configuration is most suitable and if this model can predict LOC for changing aerodynamic characteristics, wind conditions, quadcopter types, and LOC events. One-hundred and seventy-two real-world LOC events were conducted using a 53 g Tiny Whoop, a 73 g URUAV UZ85, and a 265 g GEPRC CineGO quadcopter. For these flights, LOC was initiated by demanding an excessive yaw rate (2000 deg/s), which provokes an unrecoverable upset and subsequent crash. All RNNs were trained using only onboard sensor measurements. It was found that the commanded rotor values provided the clearest early warning signals for LOC because these values showed saturation before LOC. Moreover, all four architectures could correctly and reliably predict the impending LOC event 2 s before it actually occurred. Furthermore, to investigate generality of the methodology, the predictors were successfully applied to flight data in which the quadcopter mass, blade diameter, and blade count were varied.@en