Yu Xianjia

Yu Xianjia, Sahar Salimpour, Jorge Peña Queralta et al.

Over the last decade, robotic perception algorithms have significantly benefited from the rapid advances in deep learning (DL). Indeed, a significant amount of the autonomy stack of different commercial and research platforms relies on DL for situational awareness, especially vision sensors. This work explores the potential of general-purpose DL perception algorithms, specifically detection and segmentation neural networks, for processing image-like outputs of advanced lidar sensors. Rather than processing the three-dimensional point cloud data, this is, to the best of our knowledge, the first work to focus on low-resolution images with 360\textdegree field of view obtained with lidar sensors by encoding either depth, reflectivity, or near-infrared light in the image pixels. We show that with adequate preprocessing, general-purpose DL models can process these images, opening the door to their usage in environmental conditions where vision sensors present inherent limitations. We provide both a qualitative and quantitative analysis of the performance of a variety of neural network architectures. We believe that using DL models built for visual cameras offers significant advantages due to the much wider availability and maturity compared to point cloud-based perception.

Yu Xianjia, Jorge Peña Queralta, Jukka Heikkonen et al.

Autonomous systems are becoming inherently ubiquitous with the advancements of computing and communication solutions enabling low-latency offloading and real-time collaboration of distributed devices. Decentralized technologies with blockchain and distributed ledger technologies (DLTs) are playing a key role. At the same time, advances in deep learning (DL) have significantly raised the degree of autonomy and level of intelligence of robotic and autonomous systems. While these technological revolutions were taking place, raising concerns in terms of data security and end-user privacy has become an inescapable research consideration. Federated learning (FL) is a promising solution to privacy-preserving DL at the edge, with an inherently distributed nature by learning on isolated data islands and communicating only model updates. However, FL by itself does not provide the levels of security and robustness required by today's standards in distributed autonomous systems. This survey covers applications of FL to autonomous robots, analyzes the role of DLT and FL for these systems, and introduces the key background concepts and considerations in current research.

Yu Xianjia, Li Qingqing, Jorge Pena Queralta et al.

Unmanned aerial vehicles (UAVs) are becoming largely ubiquitous with an increasing demand for aerial data. Accurate navigation and localization, required for precise data collection in many industrial applications, often relies on RTK GNSS. These systems, able of centimeter-level accuracy, require a setup and calibration process and are relatively expensive. This paper addresses the problem of accurate positioning and navigation of UAVs through cooperative localization. Inexpensive ultra-wideband (UWB) transceivers installed on both the UAV and a support ground robot enable centimeter-level relative positioning. With fast deployment and wide setup flexibility, the proposed system is able to accommodate different environments and can also be utilized in GNSS-denied environments. Through extensive simulations and test fields, we evaluate the accuracy of the system and compare it to GNSS in urban environments where multipath transmission degrades accuracy. For completeness, we include visual-inertial odometry in the experiments and compare the performance with the UWB-based cooperative localization.

Jorge Peña Queralta, Yu Xianjia, Li Qingqing et al.

The design and development of swarms of micro-aerial vehicles (MAVs) has recently gained significant traction. Collaborative aerial swarms have potential applications in areas as diverse as surveillance and monitoring, inventory management, search and rescue, or in the entertainment industry. Swarm intelligence has, by definition, a distributed nature. Yet performing experiments in truly distributed systems is not always possible, as much of the underlying ecosystem employed requires some sort of central control. Indeed, in experimental proofs of concept, most research relies on more traditional connectivity solutions and centralized approaches. External localization solutions, such as motion capture (MOCAP) systems, visual markers, or ultra-wideband (UWB) anchors are often used. Alternatively, intra-swarm solutions are often limited in terms of, e.g., range or field-of-view. Research and development has been supported by platforms such as the e-puck, the kilobot, or the crazyflie quadrotors. We believe there is a need for inexpensive platforms such as the Crazyflie with more advanced onboard processing capabilities and sensors, while offering scalability and robust communication and localization solutions. In the following, we present a platform for research and development in aerial swarms currently under development, where we leverage Wi-Fi mesh connectivity and the distributed ROS2 middleware together with UWB ranging and communication for situated communication. We present a platform for building towards large-scale swarms of autonomous MAVs leveraging the ROS2 middleware, Wi-Fi mesh connectivity, and UWB ranging and communication. The platform is based on the Ryze Tello Drone, a Raspberry Pi Zero W as a companion computer together with a camera module, and a Decawave DWM1001 UWB module for ranging and basic communication.

Li Qingqing, Yu Xianjia, Jorge Peña Queralta et al.

Micro-aerial vehicles (MAVs) are becoming ubiquitous across multiple industries and application domains. Lightweight MAVs with only an onboard flight controller and a minimal sensor suite (e.g., IMU, vision, and vertical ranging sensors) have potential as mobile and easily deployable sensing platforms. When deployed from a ground robot, a key parameter is a relative localization between the ground robot and the MAV. This paper proposes a novel method for tracking MAVs in lidar point clouds. In lidar point clouds, we consider the speed and distance of the MAV to actively adapt the lidar's frame integration time and, in essence, the density and size of the point cloud to be processed. We show that this method enables more persistent and robust tracking when the speed of the MAV or its distance to the tracking sensor changes. In addition, we propose a multi-modal tracking method that relies on high-frequency scans for accurate state estimation, lower-frequency scans for robust and persistent tracking, and sub-Hz processing for trajectory and object identification. These three integration and processing modalities allow for an overall accurate and robust MAV tracking while ensuring the object being tracked meets shape and size constraints.