Abstract-In this paper, we present a real-time approach to local trajectory replanning for microaerial vehicles (MAVs). Current trajectory generation methods for multicopters achieve high success rates in cluttered environments, but assume that the environment is static and require prior knowledge of the map. In the presented study, we use the results of such planners and extend them with a local replanning algorithm that can handle unmodeled (possibly dynamic) obstacles while keeping the MAV close to the global trajectory. To ensure that the proposed approach is real-time capable, we maintain information about the environment around the MAV in an occupancy grid stored in a three-dimensional circular buffer, which moves together with a drone, and represent the trajectories by using uniform B-splines. This representation ensures that the trajectory is sufficiently smooth and simultaneously allows for efficient optimization.

Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper, we propose the TUM VI benchmark, a novel dataset with a diverse set of sequences in different scenes for evaluating VI odometry. It provides camera images with 1024x1024 resolution at 20 Hz, high dynamic range and photometric calibration. An IMU measures accelerations and angular velocities on 3 axes at 200 Hz, while the cameras and IMU sensors are timesynchronized in hardware. For trajectory evaluation, we also provide accurate pose ground truth from a motion capture system at high frequency (120 Hz) at the start and end of the sequences which we accurately aligned with the camera and IMU measurements. The full dataset with raw and calibrated data is publicly available. We also evaluate state-of-the-art VI odometry approaches on our dataset. * These authors contributed equally. The authors are with Technical

We present VI-DSO, a novel approach for visualinertial odometry, which jointly estimates camera poses and sparse scene geometry by minimizing photometric and IMU measurement errors in a combined energy functional. The visual part of the system performs a bundle-adjustment like optimization on a sparse set of points, but unlike key-point based systems it directly minimizes a photometric error. This makes it possible for the system to track not only corners, but any pixels with large enough intensity gradients. IMU information is accumulated between several frames using measurement preintegration, and is inserted into the optimization as an additional constraint between keyframes. We explicitly include scale and gravity direction into our model and jointly optimize them together with other variables such as poses. As the scale is often not immediately observable using IMU data this allows us to initialize our visual-inertial system with an arbitrary scale instead of having to delay the initialization until everything is observable. We perform partial marginalization of old variables so that updates can be computed in a reasonable time. In order to keep the system consistent we propose a novel strategy which we call "dynamic marginalization". This technique allows us to use partial marginalization even in cases where the initial scale estimate is far from the optimum. We evaluate our method on the challenging EuRoC dataset, showing that VI-DSO outperforms the state of the art.

No abstract

Abstract-This paper presents an architecture, protocol, and parallel algorithms for collaborative 3D mapping in the cloud with low-cost robots. The robots run a dense visual odometry algorithm on a smartphone-class processor. Key-frames from the visual odometry are sent to the cloud for parallel optimization and merging with maps produced by other robots. After optimization the cloud pushes the updated poses of the local key-frames back to the robots. All processes are managed by Rapyuta, a cloud robotics framework that runs in a commercial data center. The paper includes qualitative visualization of collaboratively built maps, as well as quantitative evaluation of localization accuracy, bandwidth usage, processing speeds, and map storage.Note to Practitioners-This paper presents an architecture for cloud-based collaborative 3D mapping with low-cost robots. The low-cost robots used in this work consist mainly of a mobile base, a smart phone class processor, an RGB-D sensor and a wireless interface. Each robot runs its own visual odometry algorithm, which estimates the pose of the robot using the color and the depth frames (images) from the RGB-D sensor. The dense visual odometry algorithm presented herein uses no image features and requires no specialized hardware. In addition to pose estimation, the visual odometry algorithm also produces key-frames, which is a subset of frames that in a way summarizes the motion of the robot. These key-frames are sent to the cloud for further optimization and merging with the key-frames produced by other robots. By sending only the key-frames (instead of all the frames produced by the sensor), bandwidth requirements are significantly reduced. Each robot is connected to the cloud infrastructure using a WebSocket-based bidirectional full duplex communication channel. The cloud infrastructure is provided using Rapyuta, a Platform-as-a-Service framework for building scalable cloud robotics applications. The key-frame pose optimization and the merging processes are parallelized in order to make them scalable. The updated key-frame poses are eventually sent back to the robot to improve its localization accuracy. In addition to describing the architecture and the design choices, the paper provides qualitative and quantitative evaluations of the integrated system.