With robotic perception constituting the biggest impediment before robots are ready for employment in real missions, the promise of more efficient and robust robotic perception in multi-agent, collaborative missions can have a great impact many robotic applications. Employing a ubiquitous and well-established visual-inertial setup onboard each agent, in this paper we propose CVI-SLAM, a novel visual-inertial framework for centralized collaborative SLAM. Sharing all information with a central server, each agent outsources computationally expensive tasks, such as global map optimization to relieve onboard resources and passes on measurements to other participating agents, while running visual-inertial odometry onboard to ensure autonomy throughout the mission. Thoroughly analyzing CVI-SLAM, we attest to its accuracy and the improvements arising from collaboration, and evaluate its scalability in the number of participating agents and applicability in terms of network requirements.

No abstract

Continuously and reliably estimating the relative configuration of robotic swarms in real-time constitutes a core functionality when pursuing the autonomy of such a swarm. Relying on external positioning systems, such as GPS or motion tracking systems, can provide the required information, but significantly limits the generality of an approach. In this letter, we target formation estimation for autonomous flights of swarms of small UAVs, as they pose particularly challenging restrictions on onboard resources, while opening up a large variety of practical scenarios for a multi-robot setup. While state of the art has been addressing efficient formation estimation, scalability remains limited to only very few agents that can be handled in real-time, with the workload of each agent depending on the total number of agents in the swarm. Aiming for scalable multi-robot systems, here we propose a distributed formation estimation approach, where the computational load of each agent is decoupled from the swarm size. This approach is implemented in a setup with minimal communication effort, requiring only ego-motion estimates from each agent and pairwise distance measurements between them, constraining their configuration globally. Evaluations on swarms of up to 49 UAVs demonstrate the power of our approach to handle large swarms, while keeping the computational load bounded for individual agents and requiring only little data exchange between two robots.

With robotic systems reaching considerable maturity in basic self-localization and environment mapping, new research avenues open up pushing for interaction of a robot with its surroundings for added autonomy. However, the transition from traditionally sparse feature-based maps to dense and accurate scene-estimation imperative for realistic manipulation is not straightforward. Moreover, achieving this level of scene perception in real-time from a computationally constrained and highly shaky and agile platform, such as a small an Unmanned Aerial Vehicle (UAV) is perhaps the most challenging scenario for perception for manipulation. Drawing inspiration from otherwise computationally constraining Computer Vision techniques, we present a system combining visual, inertial and depth information to achieve dense, local scene reconstruction of high precision in real-time. Our evaluation testbed is formed using ground-truth not only in the pose of the sensor-suite, but also the scene reconstruction using a highly accurate laser scanner, offering unprecedented comparisons of scene estimation to ground-truth using real sensor data. Given the lack of any real, ground-truth datasets for environment reconstruction, our V4RL Dense Surface Reconstruction dataset is publicly available 1 .

Driven by the promise of leveraging the benefits of collaborative robot operation, this paper presents an approach to estimate the relative transformation between two small Unmanned Aerial Vehicles (UAVs), each equipped with a single camera and an inertial sensor, comprising the first step of any meaningful collaboration. Formation flying and collaborative object manipulation are some of the few tasks that the proposed work has direct applications on, while forming a variablebaseline stereo rig using two UAVs carrying a monocular camera each promises unprecedented effectiveness in collaborative scene estimation.Assuming an overlap in the UAVs' fields of view, in the proposed framework, each UAV runs monocular-inertial odometry onboard, while an Extended Kalman Filter fuses the UAVs' estimates and common image measurements to estimate the metrically scaled relative transformation between them, in realtime. Decoupling the direction of the baseline between the cameras of the two UAVs from its magnitude, this work enables consistent and robust estimation of the uncertainty of the relative pose estimation. Our evaluation on both on simulated data and benchmarking datasets consisting of real aerial data, reveals the power of the proposed methodology in a variety of scenarios. Videohttps://youtu.be/Amkk8X826oI

Motivated by the need for globally consistent tracking and mapping before autonomous robot navigation becomes realistically feasible, this paper presents a novel backend to monocular-inertial odometry. As some of the most challenging platforms for vision-based perception, we evaluate the performance of our system using Unmanned Aerial Vehicles (UAVs). Our experimental validation demonstrates that the proposed approach achieves drift correction and metric scale estimation from a single UAV on benchmarking datasets. Furthermore, the generality of our approach is demonstrated to achieve globally consistent maps built in a collaborative manner from two UAVs, each equipped with a monocularinertial sensor suite, showing the possible gains opened by collaboration amongst robots to perform SLAM. Videohttps://youtu.be/wbX36HBu2Eg

Visual-Inertial Odometry (VIO) has been widely used and researched to control and aid the automation of navigation of robots especially in the absence of absolute position measurements, such as GPS. However, when the observable landmarks in the scene lie far away, as in highaltitude flights for example, the fidelity of the metric scale estimate in VIO greatly degrades. Aiming to tackle this issue, in this work, we utilize the virtual stereo setup formed by two Unmanned Aerial Vehicles (UAVs), equipped with one camera and one Inertial Measurement Unit (IMU) each, exploiting their view overlap and relative distance measurements between them using onboard Ultra-Wideband (UWB) modules to enable collaborative VIO. In particular, we propose a decentralized collaborative estimation scheme, where each agent holds its own local map, achieving a low pose estimation latency, while ensuring consistency of each agents' estimates via consensus-based optimization. Following a thorough evaluation in photorealistic simulations, we demonstrate the effectiveness of the approach at high-altitude flights of up to 160m, going significantly beyond the capabilities of state-of-the-art VIO methods. Finally, we show the advantage of actively adjusting the baseline on-the-fly over a fixed, target baseline, resulting in a significant reduction of the estimation error.Videohttps://youtu.be/SdL4Jb-BQ28

Visual-Inertial Odometry (VIO) has been widely used and researched to control and aid the automation of navigation of robots especially in the absence of absolute position measurements, such as GPS. However, when observable landmarks in the scene lie far away from the robot's sensor suite, as it is the case at high altitude flights, the fidelity of estimates and the observability of the metric scale degrades greatly for these methods. Aiming to tackle this issue, in this article, we employ two Unmanned Aerial Vehicles (UAVs) equipped with one monocular camera and one Inertial Measurement Unit (IMU) each, to exploit their view overlap and relative distance measurements between them using Ultra-Wideband (UWB) modules onboard to enable collaborative VIO. In particular, we propose a novel, distributed fusion scheme enabling the formation of a virtual stereo camera rig with adjustable baseline from the two UAVs. In order to control the UAV agents autonomously, we propose a decentralized collaborative estimation scheme, where each agent hold its own local map, achieving an average pose estimation latency of 11ms, while ensuring consistency of the agents' estimates via consensus based optimization. Following a thorough evaluation on photorealistic simulations, we demonstrate the effectiveness of the approach at high altitude flights of up to 160m, going significantly beyond the capabilities of state-of-theart VIO methods.Finally, we show the advantage of actively adjusting the baseline on-the-fly over a fixed, target baseline, reducing the error in our experiments by a factor of two.