One camera and one low-cost inertial measurement unit (IMU) form a monocular visual-inertial system (VINS), which is the minimum sensor suite (in size, weight, and power) for the metric six degrees-of-freedom (DOF) state estimation. In this paper, we present VINS-Mono: a robust and versatile monocular visual-inertial state estimator. Our approach starts with a robust procedure for estimator initialization. A tightly coupled, nonlinear optimization-based method is used to obtain highly accurate visual-inertial odometry by fusing preintegrated IMU measurements and feature observations. A loop detection module, in combination with our tightly coupled formulation, enables relocalization with minimum computation. We additionally perform 4-DOF pose graph optimization to enforce the global consistency. Furthermore, the proposed system can reuse a map by saving and loading it in an efficient way. The current and previous maps can be merged together by the global pose graph optimization. We validate the performance of our system on public datasets and real-world experiments and compare against other state-of-the-art algorithms. We also perform an onboard closed-loop autonomous flight on the microaerial-vehicle platform and port the algorithm to an iOS-based demonstration. We highlight that the proposed work is a reliable, complete, and versatile system that is applicable for different applications that require high accuracy in localization. We open source our implementations for both PCs ( https://github.com/HKUST-Aerial-Robotics/VINS-Mono ) and iOS mobile devices ( https://github.com/HKUST-Aerial-Robotics/VINS-Mobile ).

VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator

Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map ), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors’ take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

/pdf/past-present-and-future-of-simultaneous-localization-and-27i1pn9khc.pdf

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age

Simultaneous Localization and Mapping (SLAM)consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications, and witnessing a steady transition of this technology to industry. We survey the current state of SLAM. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

/pdf/past-present-and-future-of-simultaneous-localization-and-dhljw0akg5.pdf

Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age

Combining visual and inertial measurements has become popular in mobile robotics, since the two sensing modalities offer complementary characteristics that make them the ideal choice for accurate visual-inertial odometry or simultaneous localization and mapping SLAM. While historically the problem has been addressed with filtering, advancements in visual estimation suggest that nonlinear optimization offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms. The problem is kept tractable and thus ensuring real-time operation by limiting the optimization to a bounded window of keyframes through marginalization. Keyframes may be spaced in time by arbitrary intervals, while still related by linearized inertial terms. We present evaluation results on complementary datasets recorded with our custom-built stereo visual-inertial hardware that accurately synchronizes accelerometer and gyroscope measurements with imagery. A comparison of both a stereo and monocular version of our algorithm with and without online extrinsics estimation is shown with respect to ground truth. Furthermore, we compare the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter. This competitive reference implementation performs tightly coupled filtering-based visual-inertial odometry. While our approach declaredly demands more computation, we show its superior performance in terms of accuracy.

/pdf/keyframe-based-visual-inertial-odometry-using-nonlinear-17tj6999kv.pdf

Keyframe-based visual-inertial odometry using nonlinear optimization

Over the past few years, there has been an increased interest in automatic facial behavior analysis and understanding. We present OpenFace 2.0 - a tool intended for computer vision and machine learning researchers, affective computing community and people interested in building interactive applications based on facial behavior analysis. OpenFace 2.0 is an extension of OpenFace toolkit and is capable of more accurate facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation. The computer vision algorithms which represent the core of OpenFace 2.0 demonstrate state-of-the-art results in all of the above mentioned tasks. Furthermore, our tool is capable of real-time performance and is able to run from a simple webcam without any specialist hardware. Finally, unlike a lot of modern approaches or toolkits, OpenFace 2.0 source code for training models and running them is freely available for research purposes.

https://par.nsf.gov/servlets/purl/10099458

OpenFace 2.0: Facial Behavior Analysis Toolkit

In this work, we present a Direct Least-Squares (DLS) method for computing all solutions of the perspective-n-point camera pose determination (PnP) problem in the general case (n ≥ 3). Specifically, based on the camera measurement equations, we formulate a nonlinear least-squares cost function whose optimality conditions constitute a system of three third-order polynomials. Subsequently, we employ the multiplication matrix to determine all the roots of the system analytically, and hence all minima of the LS, without requiring iterations or an initial guess of the parameters. A key advantage of our method is scalability, since the order of the polynomial system that we solve is independent of the number of points. We compare the performance of our algorithm with the leading PnP approaches, both in simulation and experimentally, and demonstrate that DLS consistently achieves accuracy close to the Maximum-Likelihood Estimator (MLE).

/pdf/a-direct-least-squares-dls-method-for-pnp-2y1f3v97vy.pdf

A Direct Least-Squares (DLS) method for PnP

Accurately estimating a robot's pose relative to a global scene model and precisely tracking the pose in real-time is a fundamental problem for navigation and obstacle avoidance tasks. Due to the computational complexity of localization against a large map and the memory consumed by the model, state-of-the-art approaches are either limited to small workspaces or rely on a server-side system to query the global model while tracking the pose locally. The latter approaches face the problem of smoothly integrating the server's pose estimates into the trajectory computed locally to avoid temporal discontinuities. In this paper, we demonstrate that large-scale, real-time pose estimation and tracking can be performed on mobile platforms with limited resources without the use of an external server. This is achieved by employing map and descriptor compression schemes as well as efficient search algorithms from computer vision. We derive a formulation for integrating the global pose information into a local state estimator that produces much smoother trajectories than current approaches. Through detailed experiments, we evaluate each of our design choices individually and document its impact on the overall system performance, demonstrating that our approach outperforms state-of-the-art algorithms for localization at scale.

http://www.roboticsproceedings.org/rss11/p37.pdf

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

This work investigates the relationship between system observability properties and estimator inconsistency for a Vision-aided Inertial Navigation System (VINS). In particular, first we introduce a new methodology for determining the unobservable directions of nonlinear systems by factorizing the observability matrix according to the observable and unobservable modes. Subsequently, we apply this method to the VINS nonlinear model and determine its unobservable directions analytically. We leverage our analysis to improve the accuracy and consistency of linearized estimators applied to VINS. Our key findings are evaluated through extensive simulations and experimental validation on real-world data, demonstrating the superior accuracy and consistency of the proposed VINS framework compared to standard approaches.

Camera-IMU-based localization: Observability analysis and consistency improvement

In this paper, we study estimator inconsistency in vision-aided inertial navigation systems (VINS) from the standpoint of system's observability. We postulate that a leading cause of inconsistency is the gain of spurious information along unobservable directions, which results in smaller uncertainties, larger estimation errors, and divergence. We develop an observability constrained VINS (OC-VINS), which explicitly enforces the unobservable directions of the system, hence preventing spurious information gain and reducing inconsistency. This framework is applicable to several variants of the VINS problem such as visual simultaneous localization and mapping (V-SLAM), as well as visual-inertial odometry using the multi-state constraint Kalman filter (MSC-KF). Our analysis, along with the proposed method to reduce inconsistency, are extensively validated with simulation trials and real-world experimentation.

/pdf/consistency-analysis-and-improvement-of-vision-aided-26tv9hnuka.pdf

Consistency Analysis and Improvement of Vision-aided Inertial Navigation

In this paper, we study estimator inconsistency in Vision-aided Inertial Navigation Systems (VINS). We show that standard (linearized) estimation approaches, such as the Extended Kalman Filter (EKF), can fundamentally alter the system observability properties, in terms of the number and structure of the unobservable directions. This in turn allows the influx of spurious information, leading to inconsistency. To address this issue, we propose an Observability-Constrained VINS (OC-VINS) methodology that explicitly adheres to the observability properties of the true system.We apply our approach to the Multi-State Constraint Kalman Filter (MSC-KF), and provide both simulation and experimental validation of the effectiveness of our method for improving estimator consistency.

/pdf/on-the-consistency-of-vision-aided-inertial-navigation-2l78f3zve0.pdf

Joel A. Hesch

Papers

A Direct Least-Squares (DLS) method for PnP

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Camera-IMU-based localization: Observability analysis and consistency improvement

Consistency Analysis and Improvement of Vision-aided Inertial Navigation

On the Consistency of Vision-Aided Inertial Navigation