Estimating Autonomous Vehicle Localization Error Using 2D Geographic Information
20 Jun 2019-ISPRS international journal of geo-information (Multidisciplinary Digital Publishing Institute)-Vol. 8, Iss: 6, pp 288
TL;DR: This paper investigates the use of pre-existing 2D geographic information datasets as a proxy to estimate autonomous vehicle localization error by quantifying the representation and layout of real-world phenomena.
Abstract: Accurately and precisely knowing the location of the vehicle is a critical requirement for safe and successful autonomous driving. Recent studies suggest that error for map-based localization methods are tightly coupled with the surrounding environment. Considering this relationship, it is therefore possible to estimate localization error by quantifying the representation and layout of real-world phenomena. To date, existing work on estimating localization error have been limited to using self-collected 3D point cloud maps. This paper investigates the use of pre-existing 2D geographic information datasets as a proxy to estimate autonomous vehicle localization error. Seven map evaluation factors were defined for 2D geographic information in a vector format, and random forest regression was used to estimate localization error for five experiment paths in Shinjuku, Tokyo. In the best model, the results show that it is possible to estimate autonomous vehicle localization error with 69.8% of predictions within 2.5 cm and 87.4% within 5 cm.
Citations
More filters
TL;DR: The main objective was to assess the performance potential of autonomous vehicle sensor systems to obtain high-definition maps based on only using Velodyne sensor data for creating accurate point clouds, and results have confirmed that cm-level accuracy can be achieved.
Abstract: Recent developments in sensor technologies such as Global Navigation Satellite Systems (GNSS), Inertial Measurement Unit (IMU), Light Detection and Ranging (LiDAR), radar, and camera have led to emerging state-of-the-art autonomous systems, such as driverless vehicles or UAS (Unmanned Airborne Systems) swarms. These technologies necessitate the use of accurate object space information about the physical environment around the platform. This information can be generally provided by the suitable selection of the sensors, including sensor types and capabilities, the number of sensors, and their spatial arrangement. Since all these sensor technologies have different error sources and characteristics, rigorous sensor modeling is needed to eliminate/mitigate errors to obtain an accurate, reliable, and robust integrated solution. Mobile mapping systems are very similar to autonomous vehicles in terms of being able to reconstruct the environment around the platforms. However, they differ a lot in operations and objectives. Mobile mapping vehicles use professional grade sensors, such as geodetic grade GNSS, tactical grade IMU, mobile LiDAR, and metric cameras, and the solution is created in post-processing. In contrast, autonomous vehicles use simple/inexpensive sensors, require real-time operations, and are primarily interested in identifying and tracking moving objects. In this study, the main objective was to assess the performance potential of autonomous vehicle sensor systems to obtain high-definition maps based on only using Velodyne sensor data for creating accurate point clouds. In other words, no other sensor data were considered in this investigation. The results have confirmed that cm-level accuracy can be achieved.
59 citations
TL;DR: This article provides a review of the production and uses of maps for autonomous driving and a synthesis of the opportunities and challenges and closes with 11 open research challenges for mapping for autonomousdriving.
Abstract: This article provides a review of the production and uses of maps for autonomous driving and a synthesis of the opportunities and challenges. For many years, maps have helped human drivers make better decisions, and in the future, maps will continue to play a critical role in enabling safe and successful autonomous driving. There are, however, many technical, societal, economic, and political challenges to mapping that remain unresolved. While fully autonomous driving may be some distance in the future, intermediate steps to realize the technology can be taken. These include developing an efficient and reliable storage and dissemination infrastructure, defining minimum data quality requirements, and establishing an international mapping standard. The article closes with 11 open research challenges for mapping for autonomous driving.
30 citations
Cites methods from "Estimating Autonomous Vehicle Local..."
...[80] use 2D geographic information in lieu of 3D point clouds to evaluate the environment....
[...]
01 May 2021
TL;DR: In this article, the authors quantify the effects of platooning on pavement and provide guidelines to control corresponding potential pavement damage, and a new methodology to control pavement damage due to truck platoons is introduced.
Abstract: Truck platoons have many benefits over traditional truck mobility. Truck platoons have the potential to improve safety and reduce fuel consumption between 5% and 15%, based on platoon configuration. In Illinois, trucks carry more than 50% of freight tonnage and constitute 25% of the traffic on interstates. Therefore, expected fuel savings would be significant for trucks. Deployment of truck platoons within interstate highways may have a direct effect on flexible pavement performance, as the time between consecutive axle loads (i.e., resting time) is expected to decrease significantly. Moreover, platoons could potentially accelerate pavement damage accumulation due to trucks’ channelized position, decreasing pavement service life and increasing maintenance and rehabilitation costs. The main objective of this project was to quantify the effects of truck platoons on pavements and to provide guidelines to control corresponding potential pavement damage. Finite-element models were utilized to quantify the impact of rest period on pavement damage. Recovered and accumulated strains were predicted by fitting exponential functions to the calculated strain profiles. The results suggested that strain accumulation was negligible at a truck spacing greater that 10 ft. A new methodology to control pavement damage due to truck platoons was introduced. The method optimizes trucks’ lateral positions on the pavements, and an increase in pavement service life could be achieved if all platoons follow this optimization method. Life cycle assessment and life cycle cost analysis were conducted for fully autonomous, human-driven, and mixed-traffic regimes. For example, for an analysis period of 45 years, channelized truck platoons could save life cycle costs and environmental impacts by 28% and 21% compared with human-driven trucks, respectively. Furthermore, optimum truck platoon configuration could reduce life cycle costs and environmental impacts by 48% and 36%, respectively, compared with human-driven trucks. In contrast, channelized traffic could increase pavement roughness, increasing fuel consumption by 15%, even though platooning vehicles still benefit from reduction in air drag forces. Given that truck platoons are expected to be connected only in the first phase, no actions are required by the agency. However, in the second phase when truck platoons are also expected to be autonomous, a protocol for driving trends should be established per the recommendation of this study.
4 citations
Cites background from "Estimating Autonomous Vehicle Local..."
...As to the accuracy of the sub-lanes and trucks’ ability to maintain their positions within inches, Wong et al. (2019) studied the accuracy of estimating autonomous vehicle localization systems....
[...]
01 Nov 2020
TL;DR: The proposed self-localization method for a soccer robot using an omnidirectional camera can quickly and accurately determine the position and azimuth of the soccer robot and the distance between two objects on the playing field.
Abstract: In this paper, we propose a self-localization method for a soccer robot using an omnidirectional camera. Based on the projective geometry of the omnidirectional visual system, the image distortion from the original omnidirectional image can be completely corrected, so the robot can quickly localize itself on the playing field. First, we transform the distorted omnidirectional image to a distortion-free unwrapped image of the soccer field by projective geometry. The obtained image makes the sequent field recognizable and the self-localization of the robot more convenient and accurate. Then, by geometric invariants, the correspondence between the unwrapped image and the model of the playing field is constructed. Next, the homography theory is applied to get the precise location and orientation of the robot. The simulation and experimental results show that the proposed method can quickly and accurately determine the position and azimuth of the soccer robot and the distance between two objects on the playing field.
3 citations
01 Nov 2022
TL;DR: In this paper , the main issues involved in autonomous driving are discussed in the literature, and shed light on topics that we consider requiring further development based on Google Scholar and the Web of Science (WoS) data base.
Abstract: Autonomous Driving (AD) introduces dramatic changes to the way we travel. This emerging technology has the potential to impact the transportation sector across a wide array of categories including safety, efficiency, congestion, legislation, and travel behavior. In this survey, we review the main issues involved in AD as discussed in the literature, and shed light on topics that we consider requiring further development based on Google Scholar and the Web of Science (WoS) data base. The paper also provides the results of research trends related to Autonomous Driving based on analysis of the number of search results listed in google trends. According to our research, the fields of Vehicle-to-Vehicle (V2V) and Vehicle-to-Cloud (V2C) networking are of higher interest due to the technological gaps and standardization processes. In addition, cyber and security research is in acceleration due to its importance.
1 citations
References
More filters
27 Oct 2003
TL;DR: First results on real data demonstrate, that the normal distributions transform algorithm is capable to map unmodified indoor environments reliable and in real time, even without using odometry data.
Abstract: Matching 2D range scans is a basic component of many localization and mapping algorithms. Most scan match algorithms require finding correspondences between the used features, i.e. points or lines. We propose an alternative representation for a range scan, the normal distributions transform. Similar to an occupancy grid, we subdivide the 2D plane into cells. To each cell, we assign a normal distribution, which locally models the probability of measuring a point. The result of the transform is a piecewise continuous and differentiable probability density, that can be used to match another scan using Newton's algorithm. Thereby, no explicit correspondences have to be established. We present the algorithm in detail and show the application to relative position tracking and simultaneous localization and map building (SLAM). First results on real data demonstrate, that the algorithm is capable to map unmodified indoor environments reliable and in real time, even without using odometry data.
944 citations
"Estimating Autonomous Vehicle Local..." refers background in this paper
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai et al. [5] estimate the error of 3D NDT scan matching for an area beforehand in a pre-experiment....
[...]
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai t al....
[...]
...This is because point clouds are discretized into a set of local normal distributions (ND), at a specified grid size, during the initialization step of NDT [11]....
[...]
...[5] estimate the error of 3D NDT sc n matching for an area befor hand i a pre-experiment....
[...]
...This second scan was then registered to the ND map (NDT map matching) to obtain a location....
[...]
TL;DR: Scan registration is an essential sub-task when building maps based on range finder data from mobile robots, and the problem is to deduce how the robot has moved between consecutive scans, based on the data collected.
Abstract: Scan registration is an essential sub-task when building maps based on range finder data from mobile robots. The problem is to deduce how the robot has moved between consecutive scans, based on the ...
654 citations
"Estimating Autonomous Vehicle Local..." refers background in this paper
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai et al. [5] estimate the error of 3D NDT scan matching for an area beforehand in a pre-experiment....
[...]
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai t al....
[...]
...This is because point clouds are discretized into a set of local normal distributions (ND), at a specified grid size, during the initialization step of NDT [11]....
[...]
...[5] estimate the error of 3D NDT sc n matching for an area befor hand i a pre-experiment....
[...]
...This second scan was then registered to the ND map (NDT map matching) to obtain a location....
[...]
Book•
01 Jan 2007
TL;DR: The second edition of the widely acclaimed "Geospatial analysis" guide has been updated and extended to include a major new chapter on Geocomputational Methods as discussed by the authors, addressing the full spectrum of analytical techniques that are provided within modern Geographic Information Systems (GIS) and related geospatial software products.
Abstract: This second edition of the widely acclaimed "Geospatial Analysis" guide has been updated and extended to include a major new chapter on Geocomputational Methods. It addresses the full spectrum of analytical techniques that are provided within modern Geographic Information Systems (GIS) and related geospatial software products. It is broad in its treatment of concepts and methods and representative in terms of the software that people actually use.Topics covered include: the principal concepts of geospatial analysis, their origins and methodological context; core components of geospatial analysis, including distance and directional analysis, geometrical processing, map algebra, and grid models; basic methods of exploratory spatial data analysis (ESDA) and spatial statistics, including spatial autocorrelation and spatial regression; surface analysis, including surface form analysis, gridding and interpolation methods; network and locational analysis, including shortest path calculation, traveling salesman problems; facility location and arc routing; Geocomputational methods, including Cellular automata, Agent Based Modelling, Neural Networks and Genetic Algorithms.The Guide has been designed for everyone involved in geospatial analysis, from undergraduate and postgraduate to professional analyst, software engineer and GIS practitioner. It builds upon the spatial analysis topics included in the US National Academies 'Beyond Mapping' and 'Learning to think spatially' agendas, the UK 'Spatial Literacy in Teaching' program, the NCGIA Core Curriculum and the AAAG/UCGIS Body of Knowledge. As such it provides a valuable reference guide and accompaniment to courses built around these programs.
620 citations
03 May 2010
TL;DR: This work proposes an extension to this approach to vehicle localization that yields substantial improvements over previous work in vehicle localization, including higher precision, the ability to learn and improve maps over time, and increased robustness to environment changes and dynamic obstacles.
Abstract: Autonomous vehicle navigation in dynamic urban environments requires localization accuracy exceeding that available from GPS-based inertial guidance systems. We have shown previously that GPS, IMU, and LIDAR data can be used to generate a high-resolution infrared remittance ground map that can be subsequently used for localization [4]. We now propose an extension to this approach that yields substantial improvements over previous work in vehicle localization, including higher precision, the ability to learn and improve maps over time, and increased robustness to environment changes and dynamic obstacles. Specifically, we model the environment, instead of as a spatial grid of fixed infrared remittance values, as a probabilistic grid whereby every cell is represented as its own gaussian distribution over remittance values. Subsequently, Bayesian inference is able to preferentially weight parts of the map most likely to be stationary and of consistent angular reflectivity, thereby reducing uncertainty and catastrophic errors. Furthermore, by using offline SLAM to align multiple passes of the same environment, possibly separated in time by days or even months, it is possible to build an increasingly robust understanding of the world that can be then exploited for localization. We validate the effectiveness of our approach by using these algorithms to localize our vehicle against probabilistic maps in various dynamic environments, achieving RMS accuracy in the 10cm-range and thus outperforming previous work. Importantly, this approach has enabled us to autonomously drive our vehicle for hundreds of miles in dense traffic on narrow urban roads which were formerly unnavigable with previous localization methods.
615 citations
"Estimating Autonomous Vehicle Local..." refers methods in this paper
...Existing research has focused on improving the map matching algorithms [2], as well as producing increasingly accurate High Definition maps [3]....
[...]
01 Jan 2009
TL;DR: This dissertation extends the original two-dimensional NDT registration algorithm of Biber and Straser to 3D and introduces a number of improvements and proposes to use a combination of local visual features and Colour-NDT for robust registration of coloured 3D scans.
Abstract: This dissertation is concerned with three-dimensional (3D) sensing and 3D scan representation. Three-dimensional records are important tools in several disciplines; such as medical imaging, archaeology, and mobile robotics. This dissertation proposes the normal-distributions transform, NDT, as a general 3D surface representation with applications in scan registration, localisation, loop detection, and surface-structure analysis. After applying NDT, the surface is represented by a smooth function with analytic derivatives. This representation has several attractive properties. The smooth function representation makes it possible to use standard numerical optimisation methods, such as Newton’s method, for 3D registration. This dissertation extends the original two-dimensional NDT registration algorithm of Biber and Straser to 3D and introduces a number of improvements. The 3D-NDT scan-registration algorithm is compared to current de facto standard registration algorithms. 3D-NDT scan registration with the proposed extensions is shown to be more robust, more accurate, and faster than the popular ICP algorithm. An additional benefit is that 3D-NDT registration provides a confidence measure of the result with little additional effort. Furthermore, a kernel-based extension to 3D-NDT for registering coloured data is proposed. Approaches based on local visual features typically use only a small fraction of the available 3D points for registration. In contrast, Colour-NDT uses all of the available 3D data. The dissertation proposes to use a combination of local visual features and Colour-NDT for robust registration of coloured 3D scans. Also building on NDT, a novel approach using 3D laser scans to perform appearance-based loop detection for mobile robots is proposed. Loop detection is an importantproblem in the SLAM (simultaneous localisation and mapping) domain. The proposed approach uses only the appearance of 3D point clouds to detect loops and requires nopose information. It exploits the NDT surface representation to create histograms based on local surface orientation and smoothness. The surface-shape histograms compress the input data by two to three orders of magnitude. Because of the high compression rate, the histograms can be matched efficiently to compare the appearance of two scans. Rotation invariance is achieved by aligning scans with respect to dominant surface orientations. In order to automatically determine the threshold that separates scans at loop closures from nonoverlapping ones, the proposed approach uses expectation maximisation to fit a Gamma mixture model to the output similarity measures. In order to enable more high-level tasks, it is desirable to extract semantic information from 3D models. One important task where such 3D surface analysis is useful is boulder detection for mining vehicles. This dissertation presents a method, also inspired by NDT, that provides clues as to where the pile is, where the bucket should be placed for loading, and where there are obstacles. The points of 3D point clouds are classified based on the surrounding surface roughness and orientation. Other potential applications include extraction of drivable paths over uneven surfaces.
313 citations
"Estimating Autonomous Vehicle Local..." refers background in this paper
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai et al. [5] estimate the error of 3D NDT scan matching for an area beforehand in a pre-experiment....
[...]
...The subsequent error model was then used to dynamically determine the NDT map resolution, resulting in a reduction of map size by 32.4% while keeping mean error within 0.141 m. Akai t al....
[...]
...This is because point clouds are discretized into a set of local normal distributions (ND), at a specified grid size, during the initialization step of NDT [11]....
[...]
...[5] estimate the error of 3D NDT sc n matching for an area befor hand i a pre-experiment....
[...]
...This second scan was then registered to the ND map (NDT map matching) to obtain a location....
[...]