Ing. Michal Pliska

A new robust and accurate approach for the detection and localization of flying objects with the purpose of highly dynamic aerial interception and agile multirobot interaction is presented in this article. The approach is proposed for use on board of autonomous aerial vehicles equipped with a 3-D LiDAR sensor. It relies on a novel 3-D occupancy voxel mapping method for the target detection that provides high localization accuracy and robustness with respect to varying environments and appearance changes of the target. In combination with a proposed cluster-based multitarget tracker, sporadic false positives are suppressed, state estimation of the target is provided, and the detection latency is negligible. This makes the system suitable for tasks of agile multirobot interaction, such as autonomous aerial interception or formation control where fast, precise, and robust relative localization of other robots is crucial. We evaluate the viability and performance of the system in simulated and real-world experiments which demonstrate that at a range of 20 m, our system is capable of reliably detecting a microscale UAV with an almost 100% recall, 0.2 m accuracy, and 20 ms delay.

In haptic object discrimination, the effect of gripper embodiment, action parameters, and sensory channels has not been systematically studied. We used two anthropomorphic hands and two 2-finger grippers to grasp two sets of deformable objects. On the object classification task, we found: (i) among classifiers, SVM on sensory features and LSTM on raw time series performed best across all grippers; (ii) faster compression speeds degraded performance; (iii) generalization to different grasping configurations was limited; transfer to different compression speeds worked well for the Barrett Hand only. Visualization of the feature spaces using PCA showed that gripper morphology and action parameters were the main source of variance, making generalization across embodiment or grip configurations very difficult. On the highly challenging dataset consisting of polyurethane foams alone, only the Barrett Hand achieved excellent performance. Tactile sensors can thus provide a key advantage even if recognition is based on stiffness rather than shape. The data set with 24,000 measurements is publicly available.

A unique approach for mid-air autonomous aerial interception of non-cooperating Uncrewed Aerial Vehicles (UAVs) by a flying robot equipped with a net is presented in this paper. A novel interception guidance method called Fast Response Proportional Navigation (FRPN) is proposed, designed to catch agile maneuvering targets while relying on onboard state estimation and tracking. The proposed method is compared with state-of-the-art approaches in simulations using different target trajectories of varying complexity, comprising a large amount of flight data. FRPN demonstrates the shortest response time and the highest number of interceptions, which are key parameters for agile interception. To ensure a robust transition from theory and simulation to real-world implementation, the approach avoids overfitting to specific assumptions about the target and aims to intercept a target following an unknown, general trajectory. Furthermore, the paper identifies several often overlooked problems related to tracking and estimating the target's state that can significantly affect the overall performance of the system. It proposes a novel state estimation filter based on the Interacting Multiple Model (IMM) filter and a new measurement model. Simulated experiments show that the proposed solution significantly improves estimation accuracy over commonly employed Kalman Filter approaches when dealing with general trajectories. Based on these results, the proposed filtering and guidance methods are used to implement a complete autonomous interception system, which is thoroughly evaluated in realistic simulations and tested in real-world experiments with a maneuvering target, surpassing the performance of any state-of-the-art solution.