Robust Self-localization Research Articles

Self-Localization Using Trajectory Attractors in Outdoor Environments

Self-localization in probabilistic robotics requires detailed, geographically consistent environmental maps, which increases the computational cost. In this study, we propose a simple self-localization method that does not require such maps. In the proposed method, the order structure, such as the mobile robot’s navigation route, is embedded as trajectory attractors in the state space of a nonmonotone neural network, and self-position estimation is performed by processing based on the autonomous dynamics of the network. From experiments, we demonstrated the basic performance of the proposed method, including robust self-localization in complex outdoor environments. Furthermore, self-localization is possible on multiple courses with overlapping paths by suitably varying the network dynamics based on environmental information. While issues remain, this study points to the great potential of neurodynamics-based robotic self-localization.

Visual Map-Based Localization for Intelligent Vehicles Using Around View Monitoring in Underground Parking Lots

Accurate and robust self-localization is a crucial task for intelligent vehicles. Because of limited access to GPS signals, localization in underground parking lots remains a problem. In this paper, fusion localization for intelligent vehicles using the widely available around view monitoring (AVM) is conducted by Kalman filter based on second-order Markov motion model (KF-MM2). The proposed method consists of two steps, one for visual map construction from AVM images and the other for map-based multi-scale localization. The proposed visual map consists of a series of nodes. Each node encodes both holistic and local visual features computed from AVM images, three-dimensional structure, and vehicle pose. In the localization step, the process of image-level localization is modeled as a Hidden Markov Model (HMM), in which the map nodes are hidden states. The result of image-level localization is calculated using forward algorithm by the given AVM image sequence. Then the metric localization is computed from local features matching. Finally, the metric localization is fused with the prediction by KF-MM2. The proposed method has been verified in two typical underground parking lots. Experimental results demonstrate that the proposed method can achieve an average error of 0.39 m in underground parking lots.

Analysis of Occlusion Effects for Map-Based Self-Localization in Urban Areas.

A high-definition (HD) map provides structural information for map-based self-localization, enabling stable estimation in real environments. In urban areas, there are many obstacles, such as buses, that occlude sensor observations, resulting in self-localization errors. However, most of the existing HD map-based self-localization evaluations do not consider sudden significant errors due to obstacles. Instead, they evaluate this in terms of average error over estimated trajectories in an environment with few occlusions. This study evaluated the effects of self-localization estimation on occlusion with synthetically generated obstacles in a real environment. Various patterns of synthetic occlusion enabled the analyses of the effects of self-localization error from various angles. Our experiments showed various characteristics that locations susceptible to obstacles have. For example, we found that occlusion in intersections tends to increase self-localization errors. In addition, we analyzed the geometrical structures of a surrounding environment in high-level error cases and low-level error cases with occlusions. As a result, we suggested the concept that the real environment should have to achieve robust self-localization under occlusion conditions.

Development of Edge-Node Map Based Navigation System Without Requirement of Prior Sensor Data Collection

In this study, a novel framework for autonomous robot navigation system is proposed. The navigation system uses an edge-node map, which is easily created from electronic maps. Unlike a general self-localization method using an occupancy grid map or a 3D point cloud map, there is no need to run the robot in the target environment in advance to collect sensor data. In this system, the internal sensor is mainly used for self-localization. Assuming that the robot is running on the road, the position of the robot is estimated by associating the robot’s travel trajectory with the edge. In addition, node arrival determination is performed using branch point information obtained from the edge-node map. Because this system does not use map matching, robust self-localization is possible, even in a dynamic environment.

A review on absolute visual localization for UAV

Research on unmanned aerial vehicles is growing as they are becoming less expensive and more available than before. The applications span a large number of areas and include border security, search and rescue, wildlife surveying, firefighting, precision agriculture, structure inspection, surveying and mapping, aerial photography, and recreative applications. These applications can require autonomous behavior which is only possible with a precise and robust self-localization. Until recently, the favored approach to localization was based on inertial sensors and global navigation satellite systems. However, global navigation satellite systems have multiple shortcomings related to long-distance radio communications (e.g. non-line-of-sight reception, multipath, spoofing). This motivated the development of new approaches to supplement or supplant satellite navigation. Absolute visual localization is one of the two main approaches to vision-based localization. The goal is to locate the current view of the UAV in a reference satellite map or georeferenced imagery from previous flights. Various approaches were proposed in this area and this paper review most of the literature in this field since 2015. The problematic at hand is analyzed and defined. Existing approaches are reviewed in 4 categories: template matching, feature points matching, deep learning and visual odometry.

Auxiliary Vehicle Positioning Based on Robust DOA Estimation With Unknown Mutual Coupling

As an important branch of the Internet of Vehicles (IoV), vehicle positioning has drawn extensive attention. Traditional positioning systems based on a global positioning system incur long delays, and may fail due to obstructions. In this article, we propose an auxiliary positioning architecture, whose core is to estimate the direction of arrival (DOA) of signals from landmarks, such as wireless access points, utilizing a sensor array in the vehicle. Due to space limitations, the array may be placed in an arbitrary geometry and may suffer from unknown mutual coupling. Most algorithms are only effective for sensor arrays with special geometries, e.g., a uniform linear array or rectangular array. To tackle this problem, an improved multiple signal classification algorithm is derived, which is superior to the state-of-the-art iterative method from the perspective of computational complexity. Detailed analysis concerning identifiability, computational complexity, and Cramér-Rao bounds are given. The simulation results verify the improvement of the proposed DOA estimation algorithm. The proposed architecture can obtain robust self-localization with existing vehicular ad hoc networks, and it can collaborate with other positioning systems to provide a safe driving environment.

Particle Smoother-Based Landmark Mapping for the SLAM Method of an Indoor Mobile Robot with a Non-Gaussian Detection Model

HF-band radio-frequency identification (RFID) is a robust identification system that is rarely influenced by objects in the robot activity area or by illumination conditions. An HF-band RFID system is capable of facilitating a reasonably accurate and robust self-localization of indoor mobile robots. An RFID-based self-localization system for an indoor mobile robot requires prior knowledge of the map which contains the ID information and positions of the RFID tags used in the environment. Generally, the map of RFID tags is manually built. To reduce labor costs, the simultaneous localization and mapping (SLAM) technique is designed to localize the mobile robot and build a map of the RFID tags simultaneously. In this study, multiple HF-band RFID readers are installed on the bottom of an omnidirectional mobile robot and RFID tags are spread on the floor. Because the tag detection process of the HF-band RFID system does not follow a standard Gaussian distribution, extended Kalman filter- (EKF-) based landmark updates are unsuitable. This paper proposes a novel SLAM method for the indoor mobile robot with a non-Gaussian detection model, by using the particle smoother for the landmark mapping and particle filter for the self-localization of the mobile robot. The proposed SLAM method is evaluated through experiments with the HF-band RFID system which has the non-Gaussian detection model. Furthermore, the proposed SLAM method is also evaluated by a range and bearing sensor which has the standard Gaussian detection model. In particular, the proposed method is compared against two other SLAM methods: FastSLAM and SLAM methods utilize particle filter for both the landmark updating and robot self-localization. The experimental results show the validity and superiority of the proposed SLAM method.

The ApolloScape Open Dataset for Autonomous Driving and Its Application.

Autonomous driving has attracted tremendous attention especially in the past few years. The key techniques for a self-driving car include solving tasks like 3D map construction, self-localization, parsing the driving road and understanding objects, which enable vehicles to reason and act. However, large scale data set for training and system evaluation is still a bottleneck for developing robust perception models. In this paper, we present the ApolloScape dataset [1] and its applications for autonomous driving. Compared with existing public datasets from real scenes, e.g., KITTI [2] or Cityscapes [3] , ApolloScape contains much large and richer labelling including holistic semantic dense point cloud for each site, stereo, per-pixel semantic labelling, lanemark labelling, instance segmentation, 3D car instance, high accurate location for every frame in various driving videos from multiple sites, cities and daytimes. For each task, it contains at lease 15x larger amount of images than SOTA datasets. To label such a complete dataset, we develop various tools and algorithms specified for each task to accelerate the labelling process, such as joint 3D-2D segment labeling, active labelling in videos etc. Depend on ApolloScape, we are able to develop algorithms jointly consider the learning and inference of multiple tasks. In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving. We show that practically, sensor fusion and joint learning of multiple tasks are beneficial to achieve a more robust and accurate system. We expect our dataset and proposed relevant algorithms can support and motivate researchers for further development of multi-sensor fusion and multi-task learning in the field of computer vision.

Robust self-localization method using sensor reliability map

Robust self-localization method using sensor reliability map

Real-Time Automatic Colour Calibration for NAO Humanoids

A challenge in NAO soccer robots is colour calibration. Good colour calibration can result in robust and accurate self-localization of the robot. Currently manual calibration is the only solution, which is used. In this paper, we are proposing an automatic real-time, accurate YUV colour space based colour calibration technique. In order to define average values for the desired colour classes namely orange, white, green and purple, a specified set of frames from the NAO camera are analysed. These average values are corrected by luminance analysis of a new frame and are passed to the K-means clustering algorithm as a set of initial means. In addition to these four values, a set of initial means of the K-means algorithm contains 16 values that are calculated in the following manner: the frame being processed is divided into 4 by 4 grids and the average value from every grid serves as an initial mean for K-means clustering. Consequently, colours of a similar type are combined into clusters. The final step of the proposed technique is cluster classification in which the average values of the desired colour classes are corrected by luminance analysis. As NAO cameras provide video streams in YUV format and the proposed algorithm uses this format there is no need for additional computational steps for conversation between the colour spaces. As a result, computational process is reduced compared to current techniques.

A Vision-Aided Approach to Perching a Bioinspired Unmanned Aerial Vehicle

This paper presents the implementation of a machine learning approach for replicating highly adaptive avian perching behavior. With full consideration of both the configuration of flying vehicles and perching principles, a bioinspired aerial robot comprising one flight subsystem and one perching subsystem is designed. Based on the real-time landing speed and attitude, a novel type of soft grasping mechanism for dexterous perching is proposed to provide adhesive force and absorb impact force. During the critical perching phase, the dynamics of the perching actuator change with the touchdown conditions and the type of perching target. A hybrid automation of a time-to-contact theory-based attitude controller and a robust self-localization system are utilized to regulate the desired perching maneuvers. The experimental results are provided to attest to the effectiveness of the proposed perching method.

Design of an HF-Band RFID System with Multiple Readers and Passive Tags for Indoor Mobile Robot Self-Localization.

Radio frequency identification (RFID) technology has already been explored for efficient self-localization of indoor mobile robots. A mobile robot equipped with RFID readers detects passive RFID tags installed on the floor in order to locate itself. The Monte-Carlo localization (MCL) method enables the localization of a mobile robot equipped with an RFID system with reasonable accuracy, sufficient robustness and low computational cost. The arrangements of RFID readers and tags and the size of antennas are important design parameters for realizing accurate and robust self-localization using a low-cost RFID system. The design of a likelihood model of RFID tag detection is also crucial for the accurate self-localization. This paper presents a novel design and arrangement of RFID readers and tags for indoor mobile robot self-localization. First, by considering small-sized and large-sized antennas of an RFID reader, we show how the design of the likelihood model affects the accuracy of self-localization. We also design a novel likelihood model by taking into consideration the characteristics of the communication range of an RFID system with a large antenna. Second, we propose a novel arrangement of RFID tags with eight RFID readers, which results in the RFID system configuration requiring much fewer readers and tags while retaining reasonable accuracy of self-localization. We verify the performances of MCL-based self-localization realized using the high-frequency (HF)-band RFID system with eight RFID readers and a lower density of RFID tags installed on the floor based on MCL in simulated and real environments. The results of simulations and real environment experiments demonstrate that our proposed low-cost HF-band RFID system realizes accurate and robust self-localization of an indoor mobile robot.

A Robust Self-Localization Method Based on Omnidirectional Vision for Soccer Robots

According to the high dynamics of robot soccer competition in RoboCup Middle Size League and the deficiency of the current self-localization methods,a robust self-localization method based on omnidirectional vision is proposed.The method combines the particle filter localization with the matching optimization localization,and a camera parameter auto-adjusting algorithm based on image entropy is also proposed to adapt the output of omnidirectional vision to the dynamic lighting conditions.The experimental results show that global localization can be realized effectively with the proposed method while highly accurate self-localization is achieved in real-time,and robot’s self-localization is robust to the highly dynamic environment with occlusion and varying lighting conditions.

이동 로봇의 강인 위치 추정을 위한 단안 비젼 센서와 레이저 구조광 센서의 베이시안 센서융합

This paper describes a procedure of the map-based localization for mobile robots by using a sensor fusion technique in structured environments. A combination of various sensors with different characteristics and limited sensibility has advantages in view of complementariness and cooperation to obtain better information on the environment. In this paper, for robust self-localization of a mobile robot with a monocular camera and a laser structured light sensor, environment information acquired from two sensors is combined and fused by a Bayesian sensor fusion technique based on the probabilistic reliability function of each sensor predefined through experiments. For the self-localization using the monocular vision, the robot utilizes image features consisting of vertical edge lines from input camera images, and they are used as natural landmark points in self-localization process. However, in case of using the laser structured light sensor, it utilizes geometrical features composed of corners and planes as natural landmark shapes during this process, which are extracted from range data at a constant height from the navigation floor. Although only each feature group of them is sometimes useful to localize mobile robots, all features from the two sensors are simultaneously used and fused in term of information for reliable localization under various environment conditions. To verify the advantage of using multi-sensor fusion, a series of experiments are performed, and experimental results are discussed in detail.

全方位カメラを用いたテンプレートマッチングに基づくモンテカルロ位置同定法

This paper presents a robust self-localization method based on template matching and Monte Carlo Localization in the RoboCup Middle-Size League. The method of this paper can be self-localized by template matching using information of field lines and a center circle instead of colored landmarks such as goals and corner poles. In RoboCup, real-time processing is crucial. The method can reduce computational costs of template matching using dynamically generated templates. The templates of the field are generated and matched from information of white lines and an electronic compass sensor in real-time. Moreover, the method can self-localize directly from the template matching. Thus, the kidnapped robot problem is not occurred. The experimental results indicate that the proposed method can self-localize robustly and in real-time under even partial occlusion. This method is suitable for the RoboCup Middle-Size League.

Memory‐based self‐localization using omnidirectional images

AbstractFor a robot, recognizing its location in a real environment is important in terms of visual navigation, etc. This paper proposes a memory‐based self‐localization method based on the use of omnidirectional images. In the proposed method, information that is constant relative to rotation around the axis of an omnidirectional image sensor is first extracted by generating autocorrelation images from omnidirectional images containing global information that is useful for self‐localization. Next, eigenspaces are formed from the generated autocorrelation images, and self‐localization is performed by searching for the learning images that are closest to the input image in the eigenspace. Additionally, performing self‐localization in two stages (general and local) results in robust self‐localization. Lastly, experiments were conducted using time‐series omnidirectional images that were actually captured both indoors and outdoors to verify the effectiveness of the proposed method. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(5): 56–68, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1203

Multiple-Model Based Fault Detection and Diagnosis of Internal Sensors in Mobile Robot. Detection and Diagnosis of Hard/Noise Failures of Sensor via Variable Structure Interacting Multiple-Model Estimator.

This paper proposes a multi-model based approach to detection and diagnosis of hard/noise failures of internal sensors in mobile robot. Three system modes (normal mode, hard failure mode, and noise failure modes)of each sensor are modeled. Changes of the three system modes are also modeled as switching from one mode to another in a probabilistic manner. The mode probabilities and sensor outputs are estimated based on a bank of Kalman filters, and they are interacted with each other effectively. To provide better fault decision, the model sets are switched according to the robot motion. The proposed fault detection and diagnosis (FDD) algorithm is formulated based on the variable structure interacting multiple-model (VSIMM) algorithm. The FDD algorithm is incorporated into a dead-reckoning system of our mobile robot with five internal sensors (four wheel-encoders and a yaw-rate gyro). Experimental results show that the FDD algorithm gives the correct fault decision of the sensors and the dead-reckoning system allows the robust self-localization of the robot subject to sensor failures.

Vision-based localization for mobile robots

Robust self-localization and repositioning strategies are essential capabilities for robots operating in highly dynamic environments. Environments are considered highly dynamic, if objects of interest move continuously and quickly, and if chances of hitting or getting hit by other robots are quite significant. An outstanding example for such an environment is provided by RoboCup. Vision system designs for robots used in RoboCup are based on several approaches, aimed at fitting both the mechanical characteristics of the players and the strategies and operations that the different roles or playing situations may require. This paper reviews three approaches to vision-based self-localization used in the RoboCup middle-size league competition and describes the results they achieve in the robot soccer environment for which they have been designed.