Mobile Robot Localization Method Research Articles

Appearance-based mapping and localization for mobile robots using a feature stability histogram

The strength of appearance-based mapping models for mobile robots lies in their ability to represent the environment through high-level image features and to provide human-readable information. However, developing a mapping and a localization method using these kinds of models is very challenging, especially if robots must deal with long-term mapping, localization, navigation, occlusions, and dynamic environments. In other words, the mobile robot has to deal with environmental appearance change, which modifies its representation of the environment. This paper proposes an indoor appearance-based mapping and a localization method for mobile robots based on the human memory model, which was used to build a Feature Stability Histogram (FSH) at each node in the robot topological map. This FSH registers local feature stability over time through a voting scheme, and the most stable features were considered for mapping, for Bayesian localization and for incrementally updating the current appearance reference view in the topological map. The experimental results are presented using an omnidirectional images dataset acquired over the long-term and considering: illumination changes (time of day, different seasons), occlusions, random removal of features, and perceptual aliasing. The results include a comparison with the approach proposed by Dayoub and Duckett (2008) [19] and the popular Bag-of-Words (Bazeille and Filliat, 2010) [35] approach. The obtained results confirm the viability of our method and indicate that it can adapt the internal map representation over time to localize the robot both globally and locally.

2A1-M11 ハイダイナミックレンジビジョンを用いた路面の線分抽出に基づく屋外自己位置推定法(移動ロボットの自己位置推定と地図構築)

In this paper, a vision-based localization method for an outdoor mobile robot is proposed. Drastic illumination change is one of the significant issues on outdoor vision system. We employ High Dynamic Range (HDR) vision to improve the robustness of image acquisition to illumination conditions. Our proposed method uses 2D gridmaps containing salient line segments on the road detected in images. A particle filter is employed to fuse the gyro-assisted odometry and 2D grid map matching to estimate the position of the robot. We carried out localization experiments and long distance navigation experiments in Real World Robot Challenge (Tsukuba Challenge 2010). Our robot with the proposed method successfully navigated part of the course of Tsukuba Challenge 2010.

SURF와 Particle filter를 이용한 이동 로봇의 위치 추정

본 논문에서는 SURF와 Particle filter를 이용한 이동로봇의 위치 추정 방법을 제안한다. 제안한 방법은 다음과 같다: 먼저, 이동 로봇의 위치를 찾기 위해 SURF 알고리증을 이용하여 카메라로부터 획득한 영상을 분석한다. 두 번째, 획득한 영상으로부터 이동로봇의 상대적인 위치를 알기 위해 이동로봇에 설치되어 있는 초음파 센서를 이용하여 주변 환경과의 거리를 측정한다. 그리고 측정된 센서 값들을 기반으로 하여 이동 로봇의 위치를 추정하는데 있어서 오차를 줄이고자 위치 추정에 많이 사용되는 Particle filter를 이용하여 이동 로봇의 위치를 추정한다. 마지막으로, 본 논문에서 제안한 방법은 실험을 통해 그 응용 가능성을 증명한다. In this paper, we propose the localization method of mobile robot using SURF(Speeded-Up Robust Features) and Particle filter. The proposed method is as follows: First, we seek the Landmark from the obtained image using SURF in order to find the first rigorous position of mobile robot. Second, we obtain the distance from obstacles using ultrasonic sensors in order to create the relative position of mobile robot. And then, we estimate the localization of mobile robot using Particle filter about movement of mobile robot. Finally, we show the feasibility of the proposed method through some experiments.

Mobile Robot Localization Using Biased Chirp-Spread-Spectrum Ranging

In this paper, we propose a method of mobile robot localization based on chirp-spread-spectrum (CSS) ranging. By using the CSS system, the distances between a mobile robot and CSS nodes fixed at known coordinates can be measured according to the time of flight of radio frequency signals. Based on the measured distances, the coordinates of a mobile robot can be calculated by the method of trilateration. To deal with measurement noise, an extended Kalman filter (EKF) can be applied to estimate the coordinate of the mobile robot. These measured distances, however, are not only noisy but also biased. Therefore, the estimated coordinates of the mobile robot represent inconsistent values. To solve the problem of bias, we define a scaling factor, which corresponds to the change of the magnitude of a measured distance vector that is due to biases. Based on the scaling factor, we develop a new biased measurement model and apply the EKF to our model for estimating the coordinates of a mobile robot. Through localization experiments, we evaluate the performance of the proposed algorithm.

Localization and tracking algorithm for mobile robot based on wireless sensor network

PurposeThe purpose of this paper is to describe a low‐cost mobile robot localization and navigation system based on wireless sensor network (WSN). This can be used in extreme environments such as mines, hostile areas, and other places where static nodes cannot be deployed directly.Design/methodology/approachThe distance between robot and beacon nodes is estimated by received signal strength indicator (RSSI). The adaptive Kalman filter algorithm is used to eliminate noise from the RSSI signal. Then, the paper gets the mobile robot's status information which includes position, velocity, and acceleration. In order to improve the real‐time performance of systems and reduce the computation overhead of robot's CPU, the paper chooses a beacon node by some certain rules to implement the localization program. The robot and beacon nodes use the CC2430 as the communication and data‐processing unit.FindingsThe experiment shows it has the characteristics of good position precision, is easily realized, and inexpensive.Research limitations/implicationsThat the system needs so many beacon nodes, is the main limitation.Practical implicationsA very useful and low‐cost method for mobile robot localization and navigation.Originality/valueThe innovative aspect of the paper is that it attempts an analysis of the localization system based on WSN, by attempting to analyze and explain the model of localization system which includes robot and beacon nodes.

Robust mobile robot localization in highly non-static environments

In this paper, we propose a robust pose tracking method for mobile robot localization with an incomplete map in a highly non-static environment. This algorithm will work with a simple map that does not include complete information about the non-static environment. With only an initial incomplete map, a mobile robot cannot estimate its pose because of the inconsistency between the real observations from the environment and the predicted observations on the incomplete map. The proposed localization algorithm uses the approach of sampling from a non-corrupted window, which allows the mobile robot to estimate its pose more robustly in a non-static environment even when subjected to severe corruption of observations. The algorithm sequence involves identifying the corruption by comparing the real observations with the corresponding predicted observations of all particles, sampling particles from a non-corrupted window that consists of multiple non-corrupted sets, and filtering sensor measurements to provide weights to particles in the corrupted sets. After localization, the estimated path may still contain some errors due to long-term corruption. These errors can be corrected using nonlinear constrained least-squares optimization. The incomplete map is then updated using both the corrected path and the stored sensor information. The performance of the proposed algorithm was verified via simulations and experiments in various highly non-static environments. Our localization algorithm can increase the success rate of tracking its pose to more than 95% compared to estimates made without its use. After that, the initial incomplete map is updated based on the localization result.

천정부착 랜드마크 위치와 에지 화소의 이동벡터 정보에 의한 이동로봇 위치 인식

A new indoor mobile robot localization method is presented. Robot recognizes well designed single color landmarks on the ceiling by vision system, as reference to compute its precise position. The proposed likelihood prediction based method enables the robot to estimate its position based only on the orientation of landmark.The use of single color landmarks helps to reduce the complexity of the landmark structure and makes it easily detectable. Edge based optical flow is further used to compensate for some landmark recognition error. This technique is applicable for navigation in an unlimited sized indoor space. Prediction scheme and localization algorithm are proposed, and edge based optical flow and data fusing are presented. Experimental results show that the proposed method provides accurate estimation of the robot position with a localization error within a range of 5 cm and directional error less than 4 degrees.

1A2-E25 路面画像を用いた移動ロボットの自己位置推定

This paper describe a view based localization method for mobile robot. Our proposal system use ground image as landmark to estimate of robot position. Using ground image as a landmark has several advantages that have many occasions to observe a landmark in crowd because of less occlusion and easy to create a map because of the 2-D plane. Our proposal system create a ground map by overlaying the ground images and estimate the robot position by maching feature points between the observed images and the ground map images. We realize a highly accurate self position estimate by resolving the problem of feature points matching such as feature points error and image saturated by sunlight.

넓은 실내 공간에서 반복적인 칼라패치의 6각형 배열에 의한 이동로봇의 위치계산

This paper presents a new mobile robot localization method for indoor robot navigation. The method uses hexagon distributed color-coded patches on the ceiling and a camera is installed on the robot facing the ceiling to recognize these patches. The proposed "cell-coded map", with the use of only seven different kinds of color-coded landmarks distributed in hexagonal way, helps reduce the complexity of the landmark structure and the error of landmark recognition. This technique is applicable for navigation in an unlimited size of indoor space. The structure of the landmarks and the recognition method are introduced. And 2 rigid rules are also used to ensure the correctness of the recognition. Experimental results prove that the method is useful.

RFID based Mobile Robot Localization and Pseudorandom Tag Arrangement

AbstractIn passive RFID environment, this paper presents an efficient mobile robot localization and a pseudorandom tag arrangement for improved performance. It is assumed that a mobile robot travels along a series of linear segments, each at a constant velocity, and the number of tags sensed at once is at most one. First, using the spatio-temporal information during tag traversing, a simple but effective mobile robot localization method is developed. Second, three representative tag arrangements, including square, parallelogram, and tilted square, are examined. Special attention is given to the problem of long navigation without tag sensing, so called tag invisibility. Taking into account both tag invisibility and tag installation, a pseudorandom tag arrangement, inspired from the Sudoku puzzle, is proposed. To demonstrate the validity of the proposed mobile robot localization system, some experimental results are given.

2A1-E05 屋外環境における見えに基づく広域確率的位置推定(移動ロボットのための視覚)

This paper presents a view-based localization method for vehicles and mobile robots in large-scale outdoor environments. The method works in two phases. In the first, learning phase, we acquire an image sequence while moving on a route by car. In the second, localization phase, we perform localization by comparing the input image with the learned images. An important problem in view-based outdoor localization is the change of object views due to changes of weather and seasons. Our method copes with this problem by first recognizing object by considering such view changes and then by comparing the recognition results of the learned and the input image. We use SVM (support vector machine) for object recognition and localization. We then develop a probabilistic localization method to consider the history of past movement and the uncertainty of recognition. Using a state transition model and a probabilistic model, we perform a probabilistic localization to estimate the probabilistic distribution of the car position.

다중 IR 거리센서를 이용한 이동로봇의 자기위치 인식

이 논문에서는 다수의 IR 거리센서를 이용한 실내용 이동로봇의 자기위치 추정에 관한 새로운 방법을 제안한다. 각각의 IR 거리센서로부터 획득한 거리데이터를 이용하여 장애물과 벽면의 모서리를 검출한다. 각 센서에서 측정된 데이터를 병합하여 환경지도를 작성한다. 실험을 통하여 얻어진 환경지도와 실제 환경을 비교하고 그 성능을 평가하였다. In this paper, a new localization method of indoor mobile robot using multi IR(infrared) range sensors is proposed. Each IR range sensor detects the edge of obstacles and wall using the acquired range data. The environment map is built by the merging process of the detected edge data of each sensor. The performance of proposed system is verified by the comparison of the real environment and the detected map in experiments.

Multi-hypothesis localization with a rough map using multiple visual features for outdoor navigation

We describe a method of mobile robot localization based on a rough map using stereo vision, which uses multiple visual features to detect and segment the buildings in the robot's field of view. The rough map is an inaccurate map with large uncertainties in the shapes, dimensions and locations of objects so that it can be built easily. The robot fuses odometry and vision information using extended Kalman filters to update the robot pose and the associated uncertainty based on the recognition of buildings in the map. We use a multi-hypothesis Kalman filter to generate and track Gaussian pose hypotheses. An experimental result shows the feasibility of our localization method in an outdoor environment.

ユークリッド変換に不変な特徴量を用いた二次元大域スキャンマッチング方式

This paper presents a new scan matching method for mobile robot localization and mapping. The proposed method utilizes Euclidean invariant features in order to match an input scan with a reference scan using no initial alignment. This method is capable of global scan matching in environments having curved objects. Experimental results show that our method successfully performed map building and global scan matching in a large environment (corridor) and a complex-shape environment (room) .

3개의 광 마우스를 이용한 강건한 광학식 거리주행계

This paper presents the robust mobile robot localization method exploiting redundant motion information acquired from three optical mice that are installed at the bottom of a mobile robot in a regular triangular form. First, we briefly introduce a low-cost optical motion sensor, HDNS-2000, and a commercial device driver development tools, WinDriver, to be used in this research. Second, we explain the basic principle of the mobile robot localization using the motion information from three optical mice, and propose the least squares based localization algorithm which is robust to the noisy measurement and partial malfunctioning of optical mice. Third, we describe the development of the experimental optical odometer using three PC optical mice and the user-friendly graphic monitoring program. Fourth, simulations and experiments are performed to demonstrate the validity of the proposed localization method and the operation of the developed optical odometer. Finally, along with the conclusion, we suggest some future work including the installation parameter calibration, the optical mouse remodelling, and the high-performance motion sensor adoption.

2P1-C29 測域センサの反射強度データを用いたスキャンマッチングによる移動ロボットの自己位置推定

This paper describes a new scan matching method for mobile robot localization. This method uses Laser Reflectance Intensity. We call this method the "Intensity-ICP". Compared with conventional scan matching method which is effective in only geometric featured environment, the Intensity-ICP is effective in both geometric featured and featureless environments.

A model-based method for indoor mobile robot localization using monocular vision and straight-line correspondences

A model-based method for indoor mobile robot localization is presented herein; this method relies on monocular vision and uses straight-line correspondences. A classical four-step approach has been adopted (i.e. image acquisition, image feature extraction, image and model feature matching, and camera pose computing). These four steps will be discussed with special focus placed on the critical matching problem. An efficient and simple method for searching image and model feature correspondences, which has been designed for indoor mobile robot self-location, will be highlighted: this is a three-stage method based on the interpretation tree search approach. During the first stage, the correspondence space is reduced by virtue of splitting the navigable space into view-invariant regions. In making use of the specificity of the mobile robotics frame of reference, the global interpretation tree is divided into two sub-trees; two low-order geometric constraints are then defined and applied directly on 2D–3D correspondences in order to improve pruning and search efficiency. During the last stage, the pose is calculated for each matching hypothesis and the best one is selected according to a defined error function. Test results illustrate the performance of this approach.

パーティクルフィルタを利用した自己位置推定に生じる致命的な推定誤りからの回復法

Though Monte Carlo localization is a popular method for mobile robot localization, it requires a method for recovery of large estimation error in itself. In this paper, a recovery method, which is named an expansion resetting method, is newly proposed. The combination of the expansion resetting method and the sensor resetting method, which is a typical resetting method, is also proposed. We then compared our methods and others in a simulated RoboCup environment. Typical accidents for mobile robots were produced in the simulator during trials. We could verify that the expansion resetting method was effective for recovery from small irregular changes of a robot's pose, and that the combination method could deal with both large and small irregular changes.

Mobile robot localization based on omnicamera

In this paper a method of mobile robot localization in an unknown indoor environment is presented. The robot is equipped with a single omni-directional camera. The images are transformed into polar representation. Based on the images and their polar coordinates, the natural landmarks of the environment are extracted. We recognize the following features of the environment-vertical and horizontal lines and areas of unique colour. By using images taken from the omni-camera wall plane landmarks are extracted. With a 360 degree view of the robot's environment, the robot's position can easily be estimated and this information can be used to follow its path. The method was tested with the use of mobile robot Navigator 1 in a real office environment

Vision-Based Mobile Robot Localization with Simple Artificial Landmarks

This article presents a vision-based method for mobile robot localization in partially known environments. Simple, unobtrusive artificial landmarks are used as external localization aids. The landmarks are labelled with unique code patterns, what enables unambiguous global localization. The analysis is presented which enables prediction of the uncertainty of the position and orientation of the robot relative to the landmark. Experimental evidence is provided, demonstrating that the proposed method can be reliably used over a wide range of relative positions between the camera and the landmark.