Ing. Matouš Vrba

In this paper, a novel approach for autonomously catching fast flying objects is presented, as inspired by the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020. In this competition, an autonomous Unmanned Aerial Vehicle (UAV) was used to intercept a ball carried by a fast flying drone. The presented solution utilizes a 3D LiDAR sensor for quick and robust target detection. The trajectory of the target is estimated and predicted to select a suitable interception position. The interceptor UAV is navigated into the interception position to safely approach the target. The interception position is frequently being adjusted based on the updated estimation and prediction of the target’s motion to ensure that the ball is caught in the dedicated onboard net. After a successful interception is detected, the UAV lands in a designated landing area. The proposed concept was intensively tested and refined in demanding outdoor conditions with strong winds and varying perception conditions to achieve the robustness required by both the demanding application and the competition. In the MBZIRC 2020 competition, our solution scored second place in Challenge 1 and first place in a combined Grand Challenge. This manuscript will provide a detailed description of the applied methods and an evaluation of our approach with data collected from real-world experiments. In addition, we present achievements of our R&D towards the transition from the MBZIRC competition to an autonomous drone interceptor, which was the main motivation of this challenge.

A novel approach for cooperative navigation and guidance of a micro-scale aerial vehicle by an accompanying Unmanned Aerial Vehicle (UAV) using 3D Light Detection and Ranging (LiDAR) relative localization is proposed in this paper. The use of 3D LiDARs represents a reliable way of environment perception and robust UAV self-localization in Global Navigation Satellite System (GNSS)-denied environments. However, 3D LiDARs are relatively heavy and they need to be carried by large UAV platforms. On the contrary, visual cameras are cheap, light-weight, and therefore ideal for small UAVs. However, visual self-localization methods suffer from loss of precision in texture-less environments, scale unobservability during certain maneuvers, and long-term drift with respect to the global frame of reference. Nevertheless, a micro-scale camera-equipped UAV is ideal for complementing a 3D LiDAR-equipped UAV as it can reach places inaccessible to a large UAV platform. To gain the advantages of both navigation approaches, we propose a cooperative navigation and guidance architecture utilizing a large LiDAR-equipped UAV accompanied by a small secondary UAV carrying a significantly lighter monocular camera. The primary UAV is localized by a robust LiDAR Simultaneous Localization and Mapping (SLAM) algorithm, while the secondary UAV utilizes a Visual-Inertial Odometry (VIO) approach with lower precision and reliability. The LiDAR data are used for markerless relative localization between the UAVs to enable precise guidance of the secondary UAV in the frame of reference of the LiDAR SLAM. The performance of the proposed approach has been extensively verified in simulations and real-world experiments with the algorithms running onboard the UAVs with no external localization infrastructure.

This paper presents a family of autonomous Unmanned Aerial Vehicles (UAVs) platforms designed for a diverse range of indoor and outdoor applications. The proposed UAV design is highly modular in terms of used actuators, sensor configurations, and even UAV frames. This allows to achieve, with minimal effort, a proper experimental setup for single, as well as, multi-robot scenarios. Presented platforms are intended to facilitate the transition from simulations, and simplified laboratory experiments, into the deployment of aerial robots into uncertain and hard-to-model real-world conditions. We present mechanical designs, electric configurations, and dynamic models of the UAVs, followed by numerous recommendations and technical details required for building such a fully autonomous UAV system for experimental verification of scientific achievements. To show strength and high variability of the proposed system, we present results of tens of completely different real-robot experiments in various environments using distinct actuator and sensory configurations.

The problem of safe interception of multiple intruder UAVs by a team of cooperating autonomous aerial vehicles is addressed in this paper. The presented work is motivated by the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020 where this task was simplified to an interaction with a set of static and dynamic objects (balloons and a UAV), and by a real autonomous aerial interception system of Eagle.One that our team has been working on. We propose a general control, perception, and coordination system for the fast and reliable interception of targets in a 3D environment relying only on onboard sensors and processing. The proposed methods and the entire complex multi-robot sys- tem were successfully verified in demanding desert conditions, with the main focus on reliability and fast deployment. In the MBZIRC competition, the proposed approach exhibited the greatest reliability and fastest solution. It was crucial to our team in winning the entire competition and achieving the second place in the intruder UAV interception scenario.

We present a multirotor Unmanned Aerial Vehicle (UAV) control and estimation system for supporting replicable research through realistic simulations and real-world experiments. We propose a unique multi-frame localization paradigm for estimating the states of a UAV in various frames of reference using multiple sensors simultaneously. The system enables complex missions in GNSS and GNSS-denied environments, including outdoor-indoor transitions and the execution of redundant estimators for backing up unreliable localization sources. Two feedback control designs are presented: one for precise and aggressive maneuvers, and the other for stable and smooth flight with a noisy state estimate. The proposed control and estimation pipeline are constructed without using the Euler/Tait-Bryan angle representation of orientation in 3D. Instead, we rely on rotation matrices and a novel heading-based convention to represent the one free rotational degree-of-freedom in 3D of a standard multirotor helicopter. We provide an actively maintained and well-documented open-source implementation, including realistic simulation of UAV, sensors, and localization systems. The proposed system is the product of years of applied research on multi-robot systems, aerial swarms, aerial manipulation, motion planning, and remote sensing. All our results have been supported by real-world system deployment that subsequently shaped the system into the form presented here. In addition, the system was utilized during the participation of our team from the Czech Technical University in Prague in the prestigious MBZIRC 2017 and 2020 robotics competitions, and also in the DARPA Subterranean challenge. Each time, our team was able to secure top places among the best competitors from all over the world.

In this letter we present an autonomous system intended for aerial monitoring, inspection and assistance in Search and Rescue (SAR) operations within a constrained workspace. The proposed system is designed for deployment in demanding real-world environments with extremely narrow passages only slightly wider than the aerial platform, and with limited visibility due to the absence of illumination and the presence of dust. The focus is on precise localization in an unknown environment, high robustness, safety and fast deployment without any need to install an external infrastructure such as an external computer and localization system. These are the main requirements of the targeted SAR scenarios. The performance of the proposed system was successfully evaluated in the Tunnel Circuit of the DARPA Subterranean Challenge, where the UAV cooperated with ground robots to precisely localize artifacts in a coal mine tunnel system. The challenge was unique due to the intention of the organizers to emulate the unpredictable conditions of a real SAR operation, in which there is no prior knowledge of the obstacles that will be encountered.

A relative localization system for micro aerial vehicles (MAVs), which is able to work without any markers or other specialized equipment, is presented in this letter. The system utilizes images from an onboard camera to detect nearby MAVs using a convolutional neural network. When compared to traditional computer vision-based relative localization systems, this approach removes the need for specialized markers to be placed on the MAVs, saving weight and space, while also enabling localization of noncooperating robots. The system is designed and implemented to run online, onboard an MAV platform in order to enable relative stabilization of several MAVs in a formation or swarm-like behavior, when operating in a closed feedback loop with the control system of the MAVs. We demonstrate the viability and robustness of the proposed method in real-world experiments. The method was also designed for the purpose of autonomous aerial interception and is a fitting complement to other MAV detection and relative localization methods for this purpose, as is shown in the experiments.

By leveraging our relative Micro-scale Unmanned Aerial Vehicle localization sensor UVDAR, we generated an automatically annotated dataset MIDGARD, which the community is invited to use for training and testing their machine learning systems for the detection and localization of Microscale Unmanned Aerial Vehicles (MAVs) by other MAVs. Furthermore, we provide our system as a mechanism for rapidly generating custom annotated datasets specifically tailored for the needs of a given application. The recent literature is rich in applications of machine learning methods in automation and robotics. One particular subset of these methods is visual object detection and localization, using means such as Convolutional Neural Networks, which nowadays enable objects to be detected and classified with previously inconceivable precision and reliability. Most of these applications, however, rely on a carefully crafted training dataset of annotated camera footage. These must contain the objects of interest in environments similar to those where the detector is expected to operate. Notably, the positions of the objects must be provided in annotations. For non-laboratory settings, the construction of such datasets requires many man-hours of manual annotation, which is especially the case for use onboard Micro-scale Unmanned Aerial Vehicles. In this paper, we are providing for the community a practical alternative to that kind of approach.

In this letter, a novel approach to fast three-dimensional (3-D) localization of flying objects for their interception by a micro aerial vehicle (MAV) is presented. The proposed method utilizes a depth image from a stereo camera to facilitate onboard detection of drones, flying in its proximity. The method does not rely on using any kind of markers, which enables localization of non-cooperating drones. This approach strongly relaxes the requirements on the drones to be detected, and the detection algorithm is computationally undemanding enough to process images online, onboard an MAV with limited computational resources. This allows using the detection system in the control feedback of an autonomous aerial intercepting system. Output of the detection algorithm is filtered by a 3-D multi-target tracking algorithm to reduce false positives, preserve temporal consistency of the detections, and to predict positions of the drones (e.g., to compensate camera and processing delays). We demonstrate the importance of the advances in flying object localization, presented in this letter, in an experiment with an intruder-interceptor scenario, which would be unfeasible using state-of-the-art detection and localization methods.

Techniques designed for using teams of small and therefore safe Micro Aerial Vehicles (MAVs) for realization of antenna-like sensing devices with flexible shape, which may be adaptively changed based on the currently sensed properties of the scanned medium, are presented in this paper. This approach enables using simple and cheap sensors carried onboard of MAVs and cooperatively deploying them in the environment to optimize overall sensitivity of the compound sensory array. Two case studies of a deployment of MAV teams in the application of real-time radio transmitters localization are discussed as an example. The first method relies on Kalman Filter-based fusion of distributed RSSI measurements used to estimate distances between the transmitter and multiple receivers, which results in precise, robust and fast transmitters location in the environment. The second method utilizes onboard rotating directional antennas to estimate angles between transmitters and receivers at different positions and a Weighted Robust Least Squares method to determine transmitters locations. Both algorithms were verified in a realistic simulation system under Gazebo simulator in ROS and in real experiments with a fleet of MAVs, with a focus on aspects of real-time information fusion and coordination of MAVs sharing the same workspace with small mutual distances.