For the effective deployment of countermeasures against drones, information on their intent is crucial. There are several indicators for a drone's intent, for example, its size, payload and behaviour. In this paper, a method is proposed to estimate two or more of the following four indicators: a drone's wing type, its number of rotors, the presence of a payload and its mean rotor rotation rate. Specifically, three multitask learning (MTL) approaches are analysed for the simultaneous estimation of several of these indicators based on radar micro-Doppler spectrograms. MTL refers to training neural networks simultaneously for multiple related tasks. The assumption is that if tasks share features between them, an MTL model is easier to train and has improved generalisation capabilities as compared to separately trained single-task neural networks. The proposed MTL approaches are validated with experimental data and in a variety of combined classification and regression tasks. The results show that MTL approaches can provide improvement in several tasks compared with conventional approaches.

Synthetic aperture radar (SAR) processing on agile radar platforms requires a very accurate estimate of position due to the unpredictable trajectory of such platforms. This is even more challenging in GPS-denied scenarios where the bias in inertial sensors cannot be compensated. In this study, we propose a 3D radar-Aided positioning method based on SAR autofocusing to achieve subresolution positioning accuracy. The proposed multibeam autofocus algorithm builds on multiple SAR motion compensation techniques to generalize and provide a framework for simultaneous omnidirectional imaging and trajectory estimation and correction while taking advantage of the beamforming capabilities of the antenna array. Our initial simulations and proof of concept show that the performance of the proposed approach is adequate even in low signal-To-noise ratio cases.