Vehicle Odometry Research Articles

A novel 3D LiDAR deep learning approach for uncrewed vehicle odometry.

Self-localization and pose registration are required for sound operation of next generation autonomous vehicles under uncertain environments. Thus, precise localization and mapping are crucial tasks in odometry, planning and other downstream processing. In order to reduce information loss in preprocessing, we propose leveraging LiDAR-based localization and mapping (LOAM) with point cloud-based deep learning instead of convolutional neural network (CNN) based methods that require cylindrical projection. The normal distribution transform (NDT) algorithm is then used to refine the former coarse pose estimation from the deep learning model. The results demonstrate that the proposed method is comparable in performance to recent benchmark studies. We also explore the possibility of using Product Quantization to improve NDT internal neighborhood searching by using high-level features as fingerprints.

NALO-VOM: Navigation-Oriented LiDAR-Guided Monocular Visual Odometry and Mapping for Unmanned Ground Vehicles

NALO-VOM: Navigation-Oriented LiDAR-Guided Monocular Visual Odometry and Mapping for Unmanned Ground Vehicles

Four years of multimodal odometry and mapping on the rail vehicles

AbstractPrecise, seamless, and efficient train localization as well as long‐term railway environment monitoring is the essential property towards reliability, availability, maintainability, and safety engineering for railroad systems. Simultaneous localization and mapping is right at the core of solving the two problems concurrently. To this end, we propose a high‐performance and versatile multimodal framework in this paper, targeted for the odometry and mapping task for various rail vehicles. Our system is built atop an inertial‐centric state estimator that tightly couples light detection and ranging (LiDAR), visual, optionally satellite navigation, and map‐based localization information with the convenience and extendibility of loosely coupled methods. The inertial sensors inertial measurement unit and wheel encoder are treated as the primary sensor, which achieves the observations from subsystems to constrain the accelerometer and gyroscope biases. Compared with point‐only LiDAR‐inertial methods, our approach leverages more geometry information by introducing both track plane and electric power pillars into state estimation. The visual‐inertial subsystem also utilizes the environmental structure information by employing both lines and points. Besides, the method is capable of handling sensor failures by automatic reconfiguration bypassing failure modules. Our proposed method has been extensively tested in the long‐during railway environments over 4 years, including general‐speed, high‐speed, and metro, where both passenger and freight traffic are investigated. Further, we aim to share, in an open way, the experiences, problems, and successes of our group with the robotics community so that those who work in such environments can avoid these errors. In this view, we open source some of the data sets to benefit the research community.

Localization in Global Positioning System–Denied Environments Using Infrastructure-Embedded Analog-Digital Information

<div>While a majority of transportation and mobility solutions rely on in-vehicle sensors and the availability of the global positioning system (GPS) for absolute localization, alternate paradigms leveraging smart infrastructure have started becoming a viable solution for localization without needing GPS. However, the majority of approaches involving smart infrastructure require a means for wireless communication. In this article, we describe a novel method that can accurately localize the vehicle without using GPS and wireless communication by leveraging embedded digital and analog information on the roadside signage. The embedded information consists of a digital signature which can be used to cross-reference the ground truth (GT) location of the signage, as well as geometric information of the signage. This information is directly leveraged by on-vehicle sensors to generate absolute localization information. Specifically, the smart infrastructure consists of signage that is visible primarily in the infrared (IR) spectrum. A specialized camera that is optimized to read the digital signature extracts the analog information associated with the signage (ground truth and geometry). This is then used by both the camera, as well as a millimeter (mm)-wave radar to produce independent localization information. The camera and radar information are correlated with the signage information using a global nearest neighbor algorithm, followed by fusion with vehicle odometry using an extended Kalman filter (EKF) to generate accurate localization of the vehicle. The EKF is set up to manage asynchronous observations between the camera, radar, and vehicle odometry. The proposed method is implemented to localize a vehicle without the aid of GPS, and the results show consistent localization with the root mean squared (RMS) longitudinal and lateral errors less than 0.46 m and 0.19 m, respectively.</div>

Autonomous vehicle navigation using high-definition maps through CARLA-ROS simulator bridge

Autonomous vehicles (AV) have garnered significant interest in recent years due to its potential for controlling thousands of accidents that happen yearly due to human error. However, AV bring with it very complex and sophisticated requirements and challenges related to extensive testing of the algorithms and hardware in the physical world. The evolution of automotive simulation tools provides an opportunity to fully test and validate AV architectures without the risk of creating hazardous situations in real world. This research demonstrates the application of HD (High Definition) maps in autonomous vehicle navigation using ROS interface integrated with the CARLA (CAR Learning to Act) simulator. The sensor data includes Light Detection and Ranging (LiDAR), RGB-Depth (RGB-D), and vehicle odometry. HD maps play an important role in robustness of the autonomous systems where due to sensor obstruction or weather conditions the vehicle is unable to perceive the information ahead. It also aids the vehicle to sense its environment even outside from the sensor’s field of view. The research is divided into the three fundamental concepts of Simultaneous Localization and Mapping (SLAM) approach that is, (i) mapping, (ii) localization, and (iii) navigation. Two ROS tools are used for mapping, (a) OctoMap mapping, and (ii) Real-Time Appearance-Based Mapping (RTAB-Map). We demonstrate the effectiveness of localization using RTAB-Map and compare actual path, position and orientation to their estimated equivalents. Our results show acceptable error in XY axes and exemplifies the error accumulated in Z axis.

Persistent Mapping of Sensor Data for Medium-Term Autonomy.

For vehicles to operate in unmapped areas with some degree of autonomy, it would be useful to aggregate and store processed sensor data so that it can be used later. In this paper, a tool that records and optimizes the placement of costmap data on a persistent map is presented. The optimization takes several factors into account, including local vehicle odometry, GPS signals when available, local map consistency, deformation of map regions, and proprioceptive GPS offset error. Results illustrating the creation of maps from previously unseen regions (a 100 m × 880 m test track and a 1.2 km dirt trail) are presented, with and without GPS signals available during the creation of the maps. Finally, two examples of the use of these maps are given. First, a path is planned along roads that have been seen exactly once during the mapping phase. Secondly, the map is used for vehicle localization in the absence of GPS signals.

Evolving Visual Odometry for Autonomous Underwater Vehicles

In the last years visual odometers have been improved considerably, but there is still a certain lack of robustness and reliability when used to navigate Autonomous Underwater Vehicles (AUV) in complex underwater scenarios, such as habitats colonized with Posidonia oceanica or Zostera noltii. The work presented in this paper goes one step beyond the current solutions, improving a state of the art approach to be applied in underwater applications. Tests conducted with real marine visual data grabbed in waters of the Balearic Islands from a bottom-looking camera installed on an AUV, show the progress in the vehicle displacement estimation and its viability to be used online.

An underwater vehicle odometry scheme based on visual-inertial fusion

An underwater vehicle odometry scheme based on visual-inertial fusion

An underwater vehicle odometry scheme based on visual-inertial fusion

An underwater vehicle odometry scheme based on visual-inertial fusion

Radar Odometry on $SE(3)$ With Constant Velocity Motion Prior

This letter presents an approach to estimating vehicle odometry on SE(3) using a high resolution automotive radar sensor. We combine a constant velocity SE(3) motion prior with a 3D radar point cloud measurement model in a sliding window optimization scheme. We leverage radar's highly precise radial velocity measurement to compensate for point cloud sparsity and improve data association. Our approach is tested using real-world measurements from a prototype high-resolution radar sensor. We demonstrate the results of this approach for 6D motion estimation. In addition, we show that our approach is comparable to state-of-the-art SE(2) radar odometry estimates while running a full order of magnitude faster.

Asynchronous Sensor Fusion of GPS, IMU and CAN-Based Odometry for Heavy-Duty Vehicles

In heavy-duty vehicles, multiple signals are available to estimate the vehicle's kinematics, such as Inertial Measurement Unit (IMU), Global Positioning System (GPS) and linear and angular speed readings from wheel tachometers on the internal Controller Area Network (CAN). These signals have different noise variance, bandwidth and sampling rate (being the latter, possibly, irregular). In this paper we present a non-linear sensor fusion algorithm allowing asynchronous sampling and non-causal smoothing. It is applied to achieve accuracy improvements when incorporating odometry measurements from CAN bus to standard GPS+IMU kinematic estimation, as well as the robustness against missing data. Our results show that this asynchronous multi-sensor (GPS+IMU+CAN-based odometry) fusion is advantageous in low-speed manoeuvres, improving accuracy and robustness to missing data, thanks to non-causal filtering. The proposed algorithm is based on Extended Kalman Filter and Smoother, with exponential discretization of continuous-time stochastic differential equations, in order to process measurements at arbitrary time instants; it can provide data to subsequent processing steps at arbitrary time instants, not necessarily coincident with the original measurement ones. Given the extra information available in the smoothing case, its estimation performance is less sensitive to the noise-variance parameter setting, compared to causal filtering. Working Matlab code is provided at the end of this work.

Real-Time Vehicle Positioning and Mapping Using Graph Optimization.

In this work, we propose and evaluate a pose-graph optimization-based real-time multi-sensor fusion framework for vehicle positioning using low-cost automotive-grade sensors. Pose-graphs can model multiple absolute and relative vehicle positioning sensor measurements and can be optimized using nonlinear techniques. We model pose-graphs using measurements from a precise stereo camera-based visual odometry system, a robust odometry system using the in-vehicle velocity and yaw-rate sensor, and an automotive-grade GNSS receiver. Our evaluation is based on a dataset with 180 km of vehicle trajectories recorded in highway, urban, and rural areas, accompanied by postprocessed Real-Time Kinematic GNSS as ground truth. We compare the architecture’s performance with (i) vehicle odometry and GNSS fusion and (ii) stereo visual odometry, vehicle odometry, and GNSS fusion; for offline and real-time optimization strategies. The results exhibit a 20.86% reduction in the localization error’s standard deviation and a significant reduction in outliers when compared with automotive-grade GNSS receivers.

Vehicle Odometry with Camera-Lidar-IMU Information Fusion and Factor-Graph Optimization

Formula Student Driverless (FSD) requires students to design and build a driverless vehicle to race on track, which incurs great demands on the odometry solution. High accuracy odometry plays a significant role in Simultaneous Localization and Mapping (SLAM) and automatic navigation mission. This paper proposes an odometry method based on Camera-Lidar-IMU information fusion and Factor-Graph optimization. It solves the problem of observation of speed and pose transformation in high speed racing scenes with sparse features. Firstly, a YoloV3-tiny object detector is used to identify cone objects captured through camera sensor, which is used to segment the object points from the Lidar pointcloud. Then, the object points are registered by utilizing the inertial measurement unit (IMU) pre-integration result as rough estimation, to obtain increment of pose transformation in horizontal plane. And a Ground Normal Vector Registration method is developed using ground points to solve increment of vertical pose transformation. These two transformation results are coupled to get a real-time odometry. At last, the odometry results and observations are optimized at the back-end with the Factor-Graph algorithm. Experiments show that the method presented in this paper performs well in real environment, and achieves high accuracy and provides a good reference for vehicle SLAM and navigation.

Monocular Visual Inertial Direct SLAM with Robust Scale Estimation for Ground Robots/Vehicles

In this paper, we present a novel method for visual-inertial odometry for land vehicles. Our technique is robust to unintended, but unavoidable bumps, encountered when an off-road land vehicle traverses over potholes, speed-bumps or general change in terrain. In contrast to tightly-coupled methods for visual-inertial odometry, we split the joint visual and inertial residuals into two separate steps and perform the inertial optimization after the direct-visual alignment step. We utilize all visual and geometric information encoded in a keyframe by including the inverse-depth variances in our optimization objective, making our method a direct approach. The primary contribution of our work is the use of epipolar constraints, computed from a direct-image alignment, to correct pose prediction obtained by integrating IMU measurements, while simultaneously building a semi-dense map of the environment in real-time. Through experiments, both indoor and outdoor, we show that our method is robust to sudden spikes in inertial measurements while achieving better accuracy than the state-of-the art direct, tightly-coupled visual-inertial fusion method.

Fail-Aware LIDAR-Based Odometry for Autonomous Vehicles.

Autonomous driving systems are set to become a reality in transport systems and, so, maximum acceptance is being sought among users. Currently, the most advanced architectures require driver intervention when functional system failures or critical sensor operations take place, presenting problems related to driver state, distractions, fatigue, and other factors that prevent safe control. Therefore, this work presents a redundant, accurate, robust, and scalable LiDAR odometry system with fail-aware system features that can allow other systems to perform a safe stop manoeuvre without driver mediation. All odometry systems have drift error, making it difficult to use them for localisation tasks over extended periods. For this reason, the paper presents an accurate LiDAR odometry system with a fail-aware indicator. This indicator estimates a time window in which the system manages the localisation tasks appropriately. The odometry error is minimised by applying a dynamic 6-DoF model and fusing measures based on the Iterative Closest Points (ICP), environment feature extraction, and Singular Value Decomposition (SVD) methods. The obtained results are promising for two reasons: First, in the KITTI odometry data set, the ranking achieved by the proposed method is twelfth, considering only LiDAR-based methods, where its translation and rotation errors are and 0.0041 deg/m, respectively. Second, the encouraging results of the fail-aware indicator demonstrate the safety of the proposed LiDAR odometry system. The results depict that, in order to achieve an accurate odometry system, complex models and measurement fusion techniques must be used to improve its behaviour. Furthermore, if an odometry system is to be used for redundant localisation features, it must integrate a fail-aware indicator for use in a safe manner.

A Visible and Infrared Fusion Based Visual Odometry for Autonomous Vehicles

<div class="section abstract"><div class="htmlview paragraph">An accurate and timely positioning of the vehicle is required at all times for autonomous driving. The global navigation satellite system (GNSS), even when integrated with costly inertial measurement units (IMUs), would often fail to provide high-accuracy positioning due to GNSS-challenged environments such as urban canyons. As a result, visual odometry is proposed as an effective complimentary approach. Although it’s widely recognized that visual odometry should be developed based on both visible and infrared images to address issues such as frequent changes in ambient lightening conditions, the mechanism of visible-infrared fusion is often poorly designed. This study proposes a Generative Adversarial Network (GAN) based model comprises a generator, which aims to produce a fused image combining infrared intensities and visible gradients, and a discriminator whose target is to force the fused image to retain as many details that exist mostly in visible images as possible. Based on the fused image, the Features from Accelerated Segment Test (FAST) algorithm is adopted to extract feature points which are then traced with the Lucas-Kanade (LK) algorithm in subsequent images. Furthermore, to remove mismatched feature points, the Random Sample Consensus (RANSAC) method is employed to detect the outliers iteratively and to compute the essential matrix. Experiments are conducted utilizing the KAIST benchmark dataset. A significant improve in positioning accuracy is observed from experimental results, as compared to visual odometry built upon visible and infrared images only. The proposed visual odometry can provide high-accuracy positioning when the GNSS is challenged.</div></div>

Degeneracy-Aware Imaging Sonar Simultaneous Localization and Mapping

High-frequency imaging sonar sensors have recently been applied to aid underwater vehicle localization, by providing frame-to-frame odometry measurements or loop closures over large timescales. Previous methods have often assumed a planar environment, thereby restricting the use of such algorithms mostly to seafloor mapping. We propose an algorithm to generate pose-to-pose constraints for pairs of sonar images, which may also be applied to larger sets of images, that makes no assumptions about the environmental geometry. The algorithm is sensitive to the inherent degeneracies of the imaging sonar sensor model, and may be tuned to tradeoff between providing more constraints on the sensor motion and not overfitting to noise in the measurements. For real-time localization, we fuse the resulting pair-wise sonar pose constraints with vehicle odometry in a pose graph optimization framework. We rigorously evaluate the proposed method and demonstrate improvement in accuracy over previously proposed formulations both in simulation and real-world experiments.

3D 라이다 센서와 도로 환경 지도의 비교를 통한 자율주행 자동차 위치인식 기법 검증

This paper describes our study of localization for autonomous vehicles based on a particle filter with road feature maps and lidar sensor inputs. We propose this system for vehicle localization in tunnels and underground roads when satellite signals from the US GPS, the Russian GLONASS, and the Japanese QZSS are not available. We studied sensor-based localization methods for autonomous vehicles using radar, lidar, and cameras. In this paper, we describe a localization method using a particle filter that correlates a high-resolution map with a local map constructed by 3D lidar and vehicle odometry. We validate the developed method with a real-time computing environment using actual measurements obtained from public road experiments.

ARM-VO: an efficient monocular visual odometry for ground vehicles on ARM CPUs

Localization is among the most important prerequisites for autonomous navigation. Vision-based systems have got great attention in recent years due to numerous camera advantages over other sensors. Reducing the computational burden of such systems is an active research area making them applicable to resource-constrained systems. This paper aims to propose and compare a fast monocular approach, named ARM-VO, with two state-of-the-art algorithms, LibViso2 and ORB-SLAM2, on Raspberry Pi 3. The approach is a sequential frame-to-frame scheme that extracts a sparse set of well-distributed features and tracks them in upcoming frames using Kanade–Lucas–Tomasi tracker. A robust model selection is used to avoid degenerate cases of fundamental matrix. Scale ambiguity is resolved by incorporating known camera height above ground. The method is open-sourced [ https://github.com/zanazakaryaie/ARM-VO ] and implemented in ROS mostly using NEON C intrinsics while exploiting the multi-core architecture of the CPU. Experiments on KITTI dataset showed that ARM-VO is 4–5 times faster and is the only method that can work almost real-time on Raspberry Pi 3. It achieves significantly better results than LibViso2 and is ranked second after ORB-SLAM2 in terms of accuracy.

Through-Water Stereo SLAM With Refraction Correction for AUV Localization

In this letter, we propose a novel method for underwater localization using natural visual landmarks above the water surface. High-accuracy, drift-free pose estimates are necessary for inspection tasks in underwater indoor environments, such as nuclear spent pools. Inaccuracies in robot localization degrade the quality of its obtained map. Our framework uses sparse features obtained via an onboard upward-facing stereo camera to build a global ceiling feature map. However, adopting the pinhole camera model without explicitly modeling light refraction at the water-air interface contributes to a systematic error in observations. Therefore, we use refraction-corrected projection and triangulation functions to obtain true landmark estimates. The SLAM framework jointly optimizes vehicle odometry and point landmarks in a global factor graph using an incremental smoothing and mapping backend. To the best of our knowledge, this is the first method that observes in-air landmarks through water for underwater localization. We evaluate our method via both simulation and real-world experiments in a test-tank environment. The results show accurate localization across various challenging scenarios.