This paper presents visual-inertial datasets collected on-board a micro aerial vehicle. The contain synchronized stereo images, IMU measurements and accurate ground truth. first batch of facilitates the design evaluation localization algorithms on real flight data. It was in an industrial environment contains millimeter position truth from laser tracking system. second is aimed at precise 3D reconstruction recorded room equipped with motion capture 6D pose detailed scan environment. Eleven...

An increasing number of robotic systems feature multiple inertial measurement units (IMUs). Due to competing objectives-either desired vicinity the center gravity when used in controls, or an unobstructed field view integrated a sensor setup with exteroceptive for ego-motion estimation-individual IMUs are often mounted at considerable distance. As result, they sense different accelerations platform is subjected rotational motions. In this work, we derive method spatially calibrating single...

Robust and accurate visual-inertial estimation is crucial to many of today's challenges in robotics. Being able localize against a prior map obtain driftfree pose estimates can push the applicability such systems even further. Most currently available solutions, however, either focus on single session use-case, lack localization capabilities or an end-to-end pipeline. We believe that only complete system, combining state-of-the-art algorithms, scalable multi-session mapping tools, flexible...

Visual robot navigation within large-scale, semistructured environments deals with various challenges such as computation intensive path planning algorithms or insufficient knowledge about traversable spaces. Moreover, many state-of-the-art approaches only operate locally instead of gaining a more conceptual understanding the objective. This limits complexity tasks can accomplish and makes it harder to deal uncertainties that are present in context real-time robotics applications. In this...

External effects such as shocks and temperature variations affect the calibration of visual-inertial sensor systems thus they cannot fully rely on factory calibrations. Re-calibrations performed short user-collected datasets might yield poor performance since observability certain parameters is highly dependent motion. In addition, resource-constrained (e.g., mobile phones), full-batch approaches over longer sessions quickly become prohibitively expensive. this paper, we approach...

Precisely estimating the pose of an agent in a global reference frame is crucial goal that unlocks multitude robotic applications, including autonomous navigation and collaboration. In order to achieve this, current state-of-the-art localization approaches collect data provided by one or more agents create single, consistent map, maintained over time. However, with introduction lengthier sorties growing size environments, transfers between backend server where map stored are becoming...

Flying and walking robots can use their complementary features in terms of viewpoint payload capability to the best a heterogeneous team. To this end, we present our online collaborative navigation framework for unknown challenging terrain. The method leverages flying robot's onboard monocular camera create both map visual simultaneous localization mapping dense representation environment as an elevation map. This shared knowledge from platform enables robot localize itself against global...

Environmental conditions and external effects, such as shocks, have a significant impact on the calibration parameters of visual-inertial sensor systems. Thus long-term operation these systems cannot fully rely factory calibration. Since observability certain is highly dependent motion device, using short data segments at device initialization may yield poor results. When are additionally subject to energy constraints, it also infeasible use full-batch approaches big dataset careful...

Today, rail vehicle localization is based on infrastructure-side Balises (beacons) together with on-board odometry to determine whether a segment occupied. Such coarse locking leads sub-optimal usage of the networks. New railway standards propose use moving blocks centred around vehicles increase capacity network. However, this approach requires accurate and robust position velocity estimation all vehicles. In work, we investigate applicability, challenges, limitations current visual...

Industrial facilities often require periodic visual inspections of key installations. Examining these points interest is time consuming, potentially hazardous or special equipment to reach. MAVs are ideal platforms automate this expensive and tedious task. In work we present a novel system that enables human operator teach inspection task an autonomous aerial vehicle by simply demonstrating the using handheld device. To enable robust operation in confined, GPS-denied environments, employs...

Accurate and robust real-time map generation onboard of a fixed-wing UAV is essential for obstacle avoidance, path planning, critical maneuvers such as autonomous take-off landing. Due to the computational constraints, required robustness reliability, it remains challenge deploy with an online-capable, accurate framework. While photogrammetric approaches have underlying assumptions on structure view camera, generic simultaneous localization mapping (SLAM) are computationally demanding. This...

Conventional camera calibration techniques rely on discrete reference points extracted from a set of input images. While these approaches have been applied successfully for long time, omitting all image information apart point positions at the initial stage pipeline renders correct treatment uncertainties difficult and gives rise to complications in timestamping measurements applications where exposure time cannot be neglected. Drawing inspiration visual state estimation, we employ direct...

This paper presents a method for calibrating camera underwater use. We consider the case that is encased in housing and views world through flat port. The analogous to common air calibration methods except it occurs where refraction plays significant role imaging. approach as follows. intrinsics are first calibrated using standard tools. housed then records video sequence of moving target underwater. From this sequence, parameters (refractive indices, relevant dimensions, glass thickness...

Many industrial facilities require periodic visual inspections. Often the points of interest are out reach or in potentially hazardous environment. Multi-copters ideal platforms to automate this expensive and tedious task. This video presents a system that enables human operator teach inspection task an autonomous aerial vehicle by simply demonstrating using tablet. The employs Google Tango visual-inertial mapping framework as only source pose estimates, thus enabling operation GPS-denied...

This paper discusses a large-scale and long-term mapping localization scenario using the maplab open-source framework. We present brief overview of specific algorithms in system that enable building consistent map from multiple sessions. then demonstrate such can be reused even few months later for efficient 6-DoF also new trajectories registered within existing 3D model. The datasets presented this are made publicly available.

Industrial facilities often require periodic visual inspections of key installations. Examining these points interest is time consuming, potentially hazardous or special equipment to reach. MAVs are ideal platforms automate this expensive and tedious task. In work we present a novel system that enables human operator teach inspection task an autonomous aerial vehicle by simply demonstrating the using handheld device. To enable robust operation in confined, GPS-denied environments, employs...