A dependence maximization approach towards street map-based localization
17 Dec 2015-pp 3721-3728
TL;DR: This paper presents a novel approach to 2D street map-based localization for mobile robots that navigate mainly in urban sidewalk environments and employs a computationally efficient estimator of Squared-loss Mutual Information through which it achieved near real-time performance.
Abstract: In this paper, we present a novel approach to 2D street map-based localization for mobile robots that navigate mainly in urban sidewalk environments. Recently, localization based on the map built by Simultaneous Localization and Mapping (SLAM) has been widely used with great success. However, such methods limit robot navigation to environments whose maps are prebuilt. In other words, robots cannot navigate in environments that they have not previously visited. We aim to relax the restriction by employing existing 2D street maps for localization. Finding an exact match between sensor data and a street map is challenging because, unlike maps built by robots, street maps lack detailed information about the environment (such as height and color). Our approach to coping with this difficulty is to maximize statistical dependence between sensor data and the map, and localization is achieved through maximization of a Mutual Information-based criterion. Our method employs a computationally efficient estimator of Squared-loss Mutual Information through which we achieved near real-time performance. The effectiveness of our method is evaluated through localization experiments using real-world data sets.
Citations
More filters
01 May 2017
TL;DR: A probabilistic approach to autonomous robot navigation using data from OpenStreetMap that associates tracks from Open-StreeetMap with the trails detected by the robot based on its 3D-LiDAR data, using a Markov-Chain Monte-Carlo technique.
Abstract: Publicly available map services are widely used by humans for navigation and nowadays provide almost complete road network data. When utilizing such maps for autonomous navigation with mobile robots one is faced with the problem of inaccuracies of the map and the uncertainty about the position of the robot relative to the map. In this paper, we present a probabilistic approach to autonomous robot navigation using data from OpenStreetMap that associates tracks from Open-StreeetMap with the trails detected by the robot based on its 3D-LiDAR data. It combines semantic terrain information, derived from the 3D-LiDAR data, with a Markov-Chain Monte-Carlo technique to match the tracks from OpenStreetMap with the sensor data. This enables our robot to utilize OpenStreetMap for navigation planning and to still stay on the trails during the execution of these plans. We present the results of extensive experiments carried out in real world settings that demonstrate the robustness of our system regarding the alignment of the vehicle pose relative to the OpenStreetMap data.
25 citations
Cites background from "A dependence maximization approach ..."
...[7] extracts boundaries from the structural representation of GoogleMaps and projects them to images recorded by the robot....
[...]
TL;DR: This paper proposes a novel localization approach that can be applied to sidewalks based on existing 2D street maps and employs a computationally efficient estimator of squared-loss mutual information, through which it achieves near real-time performance.
Abstract: Recently, localization methods based on detailed maps constructed using simultaneous localization and mapping have been widely used for mobile robot navigation. However, the cost of building such maps increases rapidly with expansion of the target environment. Here, we consider the problem of localization of a mobile robot based on existing 2D street maps. Although a large amount of research on this topic has been reported, the majority of the previous studies have focused on car-like vehicles that navigate on roadways; thus, the efficacy of such methods for sidewalks is not yet known. In this paper, we propose a novel localization approach that can be applied to sidewalks. Whereas roadways are typically marked, e.g. by white lines, sidewalks are not and, therefore, road boundary detection is not straightforward. Thus, obtaining exact correspondence between sensor data and a street map is complex. Our approach to overcoming this difficulty is to maximize the statistical dependence between the sensor data ...
4 citations
Cites methods from "A dependence maximization approach ..."
...Although the essence of our approach has been presented previously in a conference proceedings,[15] this paper expands on the evaluation of our system using additional experiments....
[...]
25 Apr 2019
TL;DR: The ability of the proposed system to navigate personal mobility robots is verified in two real environments.
Abstract: This study proposes two kinds of systems for building intelligent service robots, namely a sensor terminal named ”Portable” for making various personal mobility robots intelligent and a distributed sensor system for constructing an informationally structured environment consisting of laser range finders and active beacons. The sensor terminal Portable is equipped with a laser range finder and a gyro. Two types of personal mobility robot, namely standing type and wheelchair type, are made intelligent by installing Portable to provide navigation functions such as localization, obstacle detection, and path planning. The sensor system is mainly used to acquire position information about the personal mobility robots, obstacles, and moving objects (e.g., people); this information is used by Portable for navigation. The obtained information is transmitted to the robot, allowing it to operate in a complicated environment. The ability of the proposed system to navigate personal mobility robots is verified in two real environments.
3 citations
Cites background from "A dependence maximization approach ..."
...Some studies have attempted to make robots run outdoors using existing published maps, under the assumption that the cost of creating and maintaining large-scale maps is prohibitive [12][13]....
[...]
01 Jan 2019
TL;DR: A path planning framework for processing 2D maps of given pedestrian locations to provide sidewalk paths and street crossing information to allow mobile robot platforms to navigate in pedestrian environments without previous knowledge and using only the current location and destination as inputs is described.
Abstract: This paper describes a path planning framework for processing 2D maps of given pedestrian locations to provide sidewalk paths and street crossing information. The intention is to allow mobile robot platforms to navigate in pedestrian environments without previous knowledge and using only the current location and destination as inputs. Depending on location, current path planning solutions on known 2D maps (e.g. Google Maps and OpenStreetMaps) from both research and industry do not always provide explicit information on sidewalk paths and street crossings, which is a common problem in suburban/rural areas. The framework’s goal is to provide path planning by means of visual inference on 2D map images and search queries through downloadable map data. The results have shown both success and challenges in estimating viable city block paths and street crossings.
2 citations
01 Jan 2021
TL;DR: The off-line methodology for machines/robots to identify zebra crossings and their respective orientations within pedestrian environments, for the purpose of identifying street crossing ability demonstrated good capability in detecting and mapping street crossings’ locations, while also showing good results in verifying them against falsely detected objects in satellite imagery.
Abstract: This paper describes an off-line (i.e. pre-navigation) methodology for machines/robots to identify zebra crossings and their respective orientations within pedestrian environments, for the purpose of identifying street crossing ability. Not knowing crossing ability beforehand can prevent path trajectories from being accurately planned pre-navigation. As such, we propose a methodology that sources information from internet 2D maps to identify the locations of pedestrian street crossings. This information is comprised of road networks and satellite imagery of street intersections, from which the locations/orientations of zebra-pattern crossings can be identified by means of trained neural networks and proposed verification algorithms. The methodology demonstrated good capability in detecting and mapping street crossings’ locations, while also showing good results in verifying them against falsely detected objects in satellite imagery. Orientation estimation of zebra-pattern crossings, using a proposed line-scanning algorithm, was found to be within an error range of 4\(^{\circ }\) on a limited test set.
Cites background or methods from "A dependence maximization approach ..."
...The output of the proposed work is the GPS-wise locations street-crossings, which can be combined with previous works [10, 15, 16] to enhance localization and navigation mobile robots in pedestrian settings....
[...]
...Irie, Sugiyama and Tomono [10] implemented localization by applying edge matching between a 2D map and a real-world RGB camera view....
[...]
References
More filters
TL;DR: An overview is presented of the medical image processing literature on mutual-information-based registration, an introduction for those new to the field, an overview for those working in the field and a reference for those searching for literature on a specific application.
Abstract: An overview is presented of the medical image processing literature on mutual-information-based registration. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application. Methods are classified according to the different aspects of mutual-information-based registration. The main division is in aspects of the methodology and of the application. The part on methodology describes choices made on facets such as preprocessing of images, gray value interpolation, optimization, adaptations to the mutual information measure, and different types of geometrical transformations. The part on applications is a reference of the literature available on different modalities, on interpatient registration and on different anatomical objects. Comparison studies including mutual information are also considered. The paper starts with a description of entropy and mutual information and it closes with a discussion on past achievements and some future challenges.
3,121 citations
"A dependence maximization approach ..." refers methods in this paper
...Although MI has already been used to register multimodal sensor data [14] [15] [16], to our knowledge, it has never been applied to street map-based localization....
[...]
...Medical image registration is one of the well-known applications of MI [14]....
[...]
...MI has been conventionally used for registration of multi-modal images [14]....
[...]
TL;DR: A more robust algorithm is developed called MixtureMCL, which integrates two complimentary ways of generating samples in the estimation of Monte Carlo Localization algorithms, and is applied to mobile robots equipped with range finders.
1,945 citations
"A dependence maximization approach ..." refers background in this paper
...1) Formulation: Particle filters that fuse observations and the robot’s motion estimation are widely used for robust localization [19] [2]....
[...]
Proceedings Article•
30 Aug 2005TL;DR: This work presents three algorithms that consider especially the trajectory nature of the data rather than simply the current position as in the typical map-matching case, and proposes an incremental algorithm that matches consecutive portions of the trajectory to the road network.
Abstract: Vehicle tracking data is an essential "raw" material for a broad range of applications such as traffic management and control, routing, and navigation. An important issue with this data is its accuracy. The method of sampling vehicular movement using GPS is affected by two error sources and consequently produces inaccurate trajectory data. To become useful, the data has to be related to the underlying road network by means of map matching algorithms. We present three such algorithms that consider especially the trajectory nature of the data rather than simply the current position as in the typical map-matching case. An incremental algorithm is proposed that matches consecutive portions of the trajectory to the road network, effectively trading accuracy for speed of computation. In contrast, the two global algorithms compare the entire trajectory to candidate paths in the road network. The algorithms are evaluated in terms of (i) their running time and (ii) the quality of their matching result. Two novel quality measures utilizing the Frechet distance are introduced and subsequently used in an experimental evaluation to assess the quality of matching real tracking data to a road network.
633 citations
Additional excerpts
...car navigation systems) [6] [7] [8] [9]....
[...]
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
TL;DR: This paper decomposes the road detection process into two steps: the estimation of the vanishing point associated with the main (straight) part of the road, followed by the segmentation of the corresponding road area based upon the detected vanishing point.
Abstract: Given a single image of an arbitrary road, that may not be well-paved, or have clearly delineated edges, or some a priori known color or texture distribution, is it possible for a computer to find this road? This paper addresses this question by decomposing the road detection process into two steps: the estimation of the vanishing point associated with the main (straight) part of the road, followed by the segmentation of the corresponding road area based upon the detected vanishing point. The main technical contributions of the proposed approach are a novel adaptive soft voting scheme based upon a local voting region using high-confidence voters, whose texture orientations are computed using Gabor filters, and a new vanishing-point-constrained edge detection technique for detecting road boundaries. The proposed method has been implemented, and experiments with 1003 general road images demonstrate that it is effective at detecting road regions in challenging conditions.
401 citations
"A dependence maximization approach ..." refers methods in this paper
...2 [21], which uses vanishing point detection...
[...]
...Input Map Ground truth Proposed method Road detection [21] LSMI plot...
[...]