The incremental poses computed through odometry can be integrated over time to calculate the pose of a device with respect to an initial location. The resulting global pose may be used to formulate a second, consistency based, loss term in a deep odometry setting. In such cases where multiple losses are imposed on a network, the uncertainty over each output can be derived to weigh the different loss terms in a maximum likelihood setting. However, when imposing a constraint on the integrated transformation, due to how only odometry is estimated at each iteration of the algorithm, there is no information about the uncertainty associated with the global pose to weigh the global loss term. In this paper, we associate uncertainties with the output poses of a deep odometry network and propagate the uncertainties through each iteration. Our goal is to use the estimated covariance matrix at each incremental step to weigh the loss at the corresponding step while weighting the global loss term using the compounded uncertainty. This formulation provides an adaptive method to weigh the incremental and integrated loss terms against each other, noting the increase in uncertainty as new estimates arrive. We provide quantitative and qualitative analysis of pose estimates and show that our method surpasses the accuracy of the state-of-the-art Visual Odometry approaches. Then, uncertainty estimates are evaluated and comparisons against fixed baselines are provided. Finally, the uncertainty values are used in a realistic example to show the effectiveness of uncertainty quantification for localization.
Con-DSO: Learning Short-Horizon Consistency Priors for RGB-D Direct Sparse Odometry
School of Information Science, Japan Advanced Institute of Science and Technology（信息科学学系，日本科学技术先进研究院）；College of Information Engineering, Shenyang University of Chemical Technology（信息工程学院，沈阳化学工业大学）
International Institute of Information Technology Hyderabad（海得拉巴国际信息技术研究所）；Montreal Institute of Learning Algorithms (MILA)（蒙特利尔学习算法研究所）；Universite de Montreal（蒙特利尔大学）
With the success of deep learning based approaches in tackling challenging problems in computer vision, a wide range of deep architectures have recently been proposed for the task of visual odometry (VO) estimation. Most of these proposed solutions rely on supervision, which requires the acquisition of precise ground-truth camera pose information, collected using expensive motion capture systems or high-precision IMU/GPS sensor rigs. In this work, we propose an unsupervised paradigm for deep visual odometry learning. We show that using a noisy teacher, which could be a standard VO pipeline, an…
Localization is an indispensable component of a robot's autonomy stack that enables it to determine where it is in the environment, essentially making it a precursor for any action execution or planning. Although convolutional neural networks have shown promising results for visual localization, they are still grossly outperformed by state-of-the-art local feature-based techniques. In this work, we propose VLocNet, a new convolutional neural network architecture for 6-DoF global pose regression and odometry estimation from consecutive monocular images. Our multitask model incorporates hard par…
LiDAR-Inertial Odometry in Dynamic Driving Scenarios using Label Consistency Detection
Institute of Artificial Intelligence, Huazhong University of Science and Technology（华中科技大学人工智能研究院）；Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
Horizon Robotics（地平线机器人）；Huazhong University of Science and Technology（华中科技大学）
In this work, we propose a novel deep online correction (DOC) framework for monocular visual odometry. The whole pipeline has two stages: First, depth maps and initial poses are obtained from convolutional neural networks (CNNs) trained in self-supervised manners. Second, the poses predicted by CNNs are further improved by minimizing photometric errors via gradient updates of poses during inference phases. The benefits of our proposed method are twofold: 1) Different from online-learning methods, DOC does not need to calculate gradient propagation for parameters of CNNs. Thus, it saves more co…
This paper introduces the united monocular-stereo features into a visual-inertial tightly coupled odometry (UMS-VINS) for robust pose estimation. UMS-VINS requires two cameras and a low-cost inertial measurement unit (IMU). The UMS-VINS is an evolution of VINS-FUSION, which modifies the VINS-FUSION from the following three perspectives. 1) UMS-VINS extracts and tracks features from the sub-pixel plane to achieve better positions of the features. 2) UMS-VINS introduces additional 2-dimensional features from the left and/or right cameras. 3) If the visual initialization fails, the IMU propagatio…
LOG-LIO2: A LiDAR-Inertial Odometry with Efficient Uncertainty Analysis
School of Surveying and Geo-Informatics, Tongji University（同济大学测量与地理信息学院）；School of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Institute of Intelligent Vehicles, Tongji University（同济大学智能车辆研究所）
Institute of Artificial Intelligence, Huazhong University of Science and Technology（华中科技大学人工智能研究院）；Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Hangzhou Guochen Robot Technology Company Limited（杭州国辰机器人科技有限公司）
Technische Universität Berlin（柏林工业大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）
Event-based cameras are bio-inspired vision sensors whose pixels work independently from each other and respond asynchronously to brightness changes, with microsecond resolution. Their advantages make it possible to tackle challenging scenarios in robotics, such as high-speed and high dynamic range scenes. We present a solution to the problem of visual odometry from the data acquired by a stereo event-based camera rig. Our system follows a parallel tracking-and-mapping approach, where novel solutions to each subproblem (3D reconstruction and camera pose estimation) are developed with two objec…
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences（中国科学院大学深圳先进技术学院）
The SLAM system based on static scene assumption will introduce huge estimation errors when moving objects appear in the field of view. This paper proposes a novel multi-object dynamic lidar odometry (MLO) based on semantic object detection technology to solve this problem. The MLO system can provide reliable localization of robot and semantic objects and build long-term static maps in complex dynamic scenes. For ego-motion estimation, we use the environment features that take semantic and geometric consistency constraints into account in the extraction process. The filtering features are robu…
AC-LIO: Towards Asymptotic Compensation for Distortion in LiDAR-Inertial Odometry via Selective Intra-Frame Smoothing
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, China（信息工程测绘遥感国家重点实验室（LIESMARS），武汉大学，中国）；Department of Mechanical Engineering, University of Michigan-Dearborn（密歇根大学迪尔伯恩分校机械工程系）；Electronic Information School, Wuhan University, China（武汉大学电子信息学院，中国）；School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（南洋理工大学电子电气工程学院，新加坡）
For ego-motion estimation, the feature representation of the scenes is crucial. Previous methods indicate that both the low-level and semantic feature-based methods can achieve promising results. Therefore, the incorporation of hierarchical feature representation may benefit from both methods. From this perspective, we propose a novel direct feature odometry framework, named DFO, for depth estimation and hierarchical feature representation learning from monocular videos. By exploiting the metric distance, our framework is able to learn the hierarchical feature representation without supervisio…
We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods. The proposed pipeline loosely couples direct odometry and feature-based SLAM to perform three levels of parallel optimizations: (1) photometric bundle adjustment (BA) that jointly optimizes the local structure and motion, (2) geometric BA that refines keyframe poses and associated feature map points, and (3) pose graph optimization to achieve global map consistency in the presence of loop closures. This is achieved in …
Singapore University of Technology and Design（新加坡科技设计大学）；Southwest University of Science and Technology（西南科技大学）
To accomplish task efficiently in a multiple robots system, a problem that has to be addressed is Simultaneous Localization and Mapping (SLAM). LiDAR (Light Detection and Ranging) has been used for many SLAM solutions due to its superb accuracy, but its performance degrades in featureless environments, like tunnels or long corridors. Centralized SLAM solves the problem with a cloud server, which requires a huge amount of computational resources and lacks robustness against central node failure. To address these issues, we present a distributed SLAM solution to estimate the trajectory of a grou…
Omni-LIVO: Robust RGB-Colored Multi-Camera Visual-Inertial-LiDAR Odometry via Photometric Migration and ESIKF Fusion
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）；Advanced Laser Technology Lab of Anhui Province（安徽省先进激光技术实验室）；Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences（中国科学院上海技术物理研究所空间主动光电技术重点实验室）
To achieve robust and accurate state estimation for robot navigation, we propose a novel Visual Inertial Odometry(VIO) algorithm with line features upon the theory of invariant Kalman filtering and Cubature Kalman Filter (CKF). In contrast with conventional CKF, the state of the filter is constructed by a high dimensional Matrix Lie group and the uncertainty is represented using Lie algebra. To improve the robustness of system in challenging scenes, e.g. low-texture or illumination changing environments, line features are brought into the state variable. In the proposed algorithm, exponential …
The ubiquitous planes and structural consistency are the most apparent features of indoor multi-story Buildings compared with outdoor environments. In this paper, we propose a tightly coupled LiDAR-Inertial 3D SLAM framework with plane features for the multi-story building. The framework we proposed is mainly composed of three parts: tightly coupled LiDAR-Inertial odometry, extraction of representative planes of the structure, and factor graph optimization. By building a local map and inertial measurement unit (IMU) pre-integration, we get LiDAR scan-to-local-map matching and IMU measurements,…
An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
Brain-inspired Application Technology Center (BATC)（类脑应用技术中心）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）
The emergence of modern RGB-D sensors had a significant impact in many application fields, including robotics, augmented reality (AR) and 3D scanning. They are low-cost, low-power and low-size alternatives to traditional range sensors such as LiDAR. Moreover, unlike RGB cameras, RGB-D sensors provide the additional depth information that removes the need of frame-by-frame triangulation for 3D scene reconstruction. These merits have made them very popular in mobile robotics and AR, where it is of great interest to estimate ego-motion and 3D scene structure. Such spatial understanding can enable…
TRLO: An Efficient LiDAR Odometry with 3D Dynamic Object Tracking and Removal
College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学 智能科学与技术学院）；University of Chinese Academy of Sciences（中国科学院大学）
BEV-LIO(LC): BEV Image Assisted LiDAR-Inertial Odometry with Loop Closure
School of Computer Science and Technology, Guangdong University of Technology（计算机科学与技术学院，广东技术大学）；School of Electrical and Electronic Engineering, Nanyang Technological University（电子与电气工程学院，南洋理工大学）
Bias-Eliminated PnP for Stereo Visual Odometry: Provably Consistent and Large-Scale Localization
School of Data Science, Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳））；Australian Center for Robotics and School of Aerospace, Mechanical and Mechatronic Engineering, University of Sydney（机器人中心及航空航天、机械与机电工程学院，悉尼大学）
We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment. Given an embodied agent trained in a noiseless environment, our objective is to transfer the agent to a noisy environment where actuation and odometry sensor noise is present. Our method encourages the agent to maximize the consistency between the global maps generated at different time steps in a round-trip trajectory. The proposed task is completely self-supervised, not requiring any supervision from ground-truth pose data or explicit noise model. In addition, optimization…
2Fast-2Lamaa: Large-Scale Lidar-Inertial Localization and Mapping with Continuous Distance Fields
Robotics Institute, University of Toronto Institute for Aerospace Studies, Canada（多伦多大学航空航天研究所）；Robotics Institute, University of Technology Sydney, Australia（悉尼技术大学机器人研究所）
A Consistency-Improved LiDAR-Inertial Bundle Adjustment
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Aerospace Information Technology University（航空信息科技大学）；QiLu Aerospace Information Research Institute, Chinese Academy of Sciences（齐鲁航空信息研究所）；School of Electronic, Electrical and Communication Engineering（电子电气与通信工程学院）
本文提出改进一致性的 LiDAR-惯性束调整方法，通过定制参数化和估计器提升 SLAM 系统的准确性和可观测性。
REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluation
Artificial Intelligence and Robotics Lab, University of Technology of Nuremberg (UTN)（人工智能与机器人实验室，图恩技术大学（UTN））；CSIRO Robotics, DATA61, and Queensland University of Technology (QUT)（CSIRO机器人，DATA61，昆士兰理工大学（QUT））；Mobile Robotics Lab, Technical University of Munich (TUM)（移动机器人实验室，慕尼黑技术大学（TUM））；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所（MIRMI））；Mobile Robotics Lab, ETH Zurich（移动机器人实验室，苏黎世联邦理工学院）
提出 REGRACE 重定位算法，利用 LiDAR 子地图、旋转不变对象特征、图神经网络、词袋检索与几何一致性验证，在达到 SOTA 识别配准效果的同时速度提升两倍。
UISEE Technology Inc.（驭势科技有限公司）；Peking University（北京大学）；Beijing Changcheng Aviation Measurement and Control Institute（北京长城航空测控技术研究所）
We propose to leverage the local information in image sequences to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential images to alleviate uncertainty due to visual ambiguities by incorporating a visual odometry (VO) component. Specifically, we introduce two effective steps called content-augmented pose estimation and motion-based refinement. The content-augmentation step focuses on alleviating the uncertainty of pose estimation by augmenting the observation based on the co…
