Abstract: The estimation of a vehiclepsilas dynamic state is one of the most fundamental data fusion tasks for intelligent traffic applications. For that, motion models are applied in order to increase the accuracy and robustness of the estimation. This paper surveys numerous (especially curvilinear) models and compares their performance using a tracking tasks which includes the fusion of GPS and odometry data with an Unscented Kalman Filter. For evaluation purposes, a highly accurate reference trajectory has been recorded using an RTK-supported DGPS receiver. With this ground truth data, the performance of the models is evaluated in different scenarios and driving situations.

Abstract: This paper describes a biologically inspired approach to vision-only simultaneous localization and mapping (SLAM) on ground-based platforms. The core SLAM system, dubbed RatSLAM, is based on computational models of the rodent hippocampus, and is coupled with a lightweight vision system that provides odometry and appearance information. RatSLAM builds a map in an online manner, driving loop closure and relocalization through sequences of familiar visual scenes. Visual ambiguity is managed by maintaining multiple competing vehicle pose estimates, while cumulative errors in odometry are corrected after loop closure by a map correction algorithm. We demonstrate the mapping performance of the system on a 66 km car journey through a complex suburban road network. Using only a web camera operating at 10 Hz, RatSLAM generates a coherent map of the entire environment at real-time speed, correctly closing more than 51 loops of up to 5 km in length.

Abstract: Many urban navigation applications (eg, autonomous navigation, driver assistance systems) can benefit greatly from localization with centimeter accuracy Yet such accuracy cannot be achieved reliably with GPS-based inertial guidance systems, specifically in urban settings We propose a technique for high-accuracy localization of moving vehicles that utilizes maps of urban environments Our approach integrates GPS, IMU, wheel odometry, and LIDAR data acquired by an instrumented vehicle, to generate high-resolution environment maps Offline relaxation techniques similar to recent SLAM methods [2, 10, 13, 14, 21, 30] are employed to bring the map into alignment at intersections and other regions of self-overlap By reducing the final map to the flat road surface, imprints of other vehicles are removed The result is a 2-D surface image of ground reflectivity in the infrared spectrum with 5cm pixel resolution To localize a moving vehicle relative to these maps, we present a particle filter method for correlating LIDAR measurements with this map As we show by experimentation, the resulting relative accuracies exceed that of conventional GPS-IMU-odometry-based methods by more than an order of magnitude Specifically, we show that our algorithm is effective in urban environments, achieving reliable real-time localization with accuracy in the 10- centimeter range Experimental results are provided for localization in GPS-denied environments, during bad weather, and in dense traffic The proposed approach has been used successfully for steering a car through narrow, dynamic urban roads

Abstract: Visual odometry can augment or replace wheel odometry when navigating in high slip terrain which is quite important for autonomous navigation on Mars. We present a computationally efficient and robust visual odometry algorithm developed for the Mars Science Laboratory mission. This algorithm is a significant improvement over the algorithm developed for the Mars Exploration Rover Mission because it is at least four time more computationally efficient and it tracks significantly more features. The core of the algorithm is an integrated motion estimation and stereo feature tracking loop that allows for feature recovery while guiding feature correlation search to minimize computation. Results on thousands of terrestrial and Martian stereo pairs show that the algorithm can operate with no initial motion estimate while still obtaining subpixel attitude estimation performance.

Abstract: For a differential-drive mobile robot equipped with an on-board range sensor, there are six parameters to calibrate: three for the odometry (radii and distance between the wheels), and three for the pose of the sensor with respect to the robot frame. This paper describes a method for calibrating all six parameters at the same time, without the need for external sensors or devices. Moreover, it is not necessary to drive the robot along particular trajectories. The available data are the measures of the angular velocities of the wheels and the range sensor readings. The maximum-likelihood calibration solution is found in a closed form.

Abstract: This paper introduces a localization based on GPS and laser measurements for urban and non-urban outdoor environments. In this approach, the GPS pose is Kalman filtered using wheel odometry and inertial data and tightly integrated into a Monte Carlo localization based on 3D laser range data and a line feature reference map. By applying to this kind of sensor fusion, global localization as well as precise position tracking in close distance to buildings is enabled where only poor GPS observations are available. Following the description of the localization system, real world experiments demonstrate the functionality of the presented approach.

Abstract: Localization and mapping are essential elements in the design of mobile robots used for search and rescue mission. Localization is a key-function of remote control and mapping in an unstructured environment. However, in general, odometry in tracked vehicles is ambiguous because of the track slippage. To solve this problem, we developed a three-dimensional gyro-based odometry that considers the compensation of slippage on the basis of an empirical model. The method was successfully implemented in a tracked vehicle, and its validity was confirmed by initial tests in real environments. Mapping is also very important in a searching task. A small three-dimensional laser range scanner provides operators and rescue crews with a wealth of information for understanding environments. However, to obtain this information, the operators must wait a few seconds and halt the robot's operation. To solve this problem, we propose the continuous acquisition of three-dimensional environment information for tracked vehicles using the three-dimensional gyro-based odometry reported above. In this paper, odometry and continuous acquisition methods are introduced for use by tracked vehicles operating in hostile environments.

Abstract: Best Paper.- Instance-Based Action Models for Fast Action Planning.- Best Student Paper.- Precise Extraction of Partially Occluded Objects by Using HLAC Features and SVM.- Full Papers.- Probabilistic Decision Making in Robot Soccer.- Multi-robot Cooperative Localization through Collaborative Visual Object Tracking.- Cooperative Object Localization Using Line-Based Percept Communication.- Adaptive Recognition of Color-Coded Objects in Indoor and Outdoor Environments.- 3D Tracking by Catadioptric Vision Based on Particle Filters.- Improving Vision-Based Distance Measurements Using Reference Objects.- Cooperative/Competitive Behavior Acquisition Based on State Value Estimation of Others.- Beyond Frontier Exploration.- Robot Building for Preschoolers.- A Simulation Environment for Middle-Size Robots with Multi-level Abstraction.- Improving Robot Self-localization Using Landmarks' Poses Tracking and Odometry Error Estimation.- Generating Dynamic Formation Strategies Based on Human Experience and Game Conditions.- Model-Based Reinforcement Learning in a Complex Domain.- HMDP: A New Protocol for Motion Pattern Generation Towards Behavior Abstraction.- A Fuzzy Controller for Autonomous Negotiation of Stairs by a Mobile Robot with Adjustable Tracks.- Solving Large-Scale and Sparse-Reward DEC-POMDPs with Correlation-MDPs.- Short Papers (Posters).- Heuristic Reinforcement Learning Applied to RoboCup Simulation Agents.- Pareto-Optimal Offensive Player Positioning in Simulated Soccer.- Rational Passing Decision Based on Region for the Robotic Soccer.- Automatic On-Line Color Calibration Using Class-Relative Color Spaces.- An Application of Gaussian Mixtures: Colour Segmenting for the Four Legged League Using HSI Colour Space.- Model Checking Hybrid Multiagent Systems for the RoboCup.- Physical Simulation of the Dynamical Behavior of Three-Wheeled Omni-directional Robots.- Intuitive Plan Construction and Adaptive Plan Selection.- Semi-autonomous Coordinated Exploration in Rescue Scenarios.- A Deeper Look at 3D Soccer Simulations.- Mean-Shift-Based Color Tracking in Illuminance Change.- High Accuracy Navigation in Unknown Environment Using Adaptive Control.- Evolutionary Design of a Fuzzy Rule Base for Solving the Goal-Shooting Problem in the RoboCup 3D Soccer Simulation League.- Behavioral Cloning for Simulator Validation.- A Model-Based Approach to Calculating and Calibrating the Odometry for Quadruped Robots.- A Framework for Learning in Humanoid Simulated Robots.- Let Robots Play Soccer under More Natural Conditions: Experience-Based Collaborative Localization in Four-Legged League.- Strategic Layout of Multi-cameras Based on a Minimum Risk Criterion.- Region-Based Segmentation with Ambiguous Color Classes and 2-D Motion Compensation.- Multi-agent Positioning Mechanism in the Dynamic Environment.- Layered Learning for a Soccer Legged Robot Helped with a 3D Simulator.- Self-localization Using Odometry and Horizontal Bearings to Landmarks.- Incremental Generation of Abductive Explanations for Tactical Behavior.- Implementing Parametric Reinforcement Learning in Robocup Rescue Simulation.- Obtaining the Inverse Distance Map from a Non-SVP Hyperbolic Catadioptric Robotic Vision System.- Tailored Real-Time Simulation for Teams of Humanoid Robots.- Evolution of Biped Walking Using Neural Oscillators and Physical Simulation.- Robust Object Recognition Using Wide Baseline Matching for RoboCup Applications.- Detection of AIBO and Humanoid Robots Using Cascades of Boosted Classifiers.- A Scalable Hybrid Multi-robot SLAM Method for Highly Detailed Maps.- A Force Sensor Made by Diaphragm Pattern Mounted on a Deformable Circular Plate.- Crossed-Line Segmentation for Low-Level Vision.- A Neural Network-Based Approach to Robot Motion Control.- Dynamic Positioning Method Based on Dominant Region Diagram to Realize Successful Cooperative Play.- Introducing Physical Visualization Sub-league.- A Real Time Vision System for Autonomous Systems: Characterization during a Middle Size Match.- ViRbot: A System for the Operation of Mobile Robots.- Grounded Representation Driven Robot Motion Design.- Design of Design Methodology for Autonomous Robots.- Opponent Provocation and Behavior Classification: A Machine Learning Approach.- Robust Color Classification Using Fuzzy Reasoning and Genetic Algorithms in RoboCup Soccer Leagues.- Compliance Control for Biped Walking on Rough Terrain.

Abstract: In this paper, we present a real-time algorithm for local simultaneous localization and mapping (SLAM) with detection and tracking of moving objects (DATMO) in dynamic outdoor environments from a moving vehicle equipped with a laser scanner. To correct vehicle location from odometry we introduce a new fast implementation of incremental scan matching method that can work reliably in dynamic outdoor environments. After a good vehicle location is estimated, the surrounding map is updated incrementally and moving objects are detected without a priori knowledge of the targets. Detected moving objects are finally tracked by a multiple hypothesis tracker (MHT) coupled with an adaptive IMM (interacting multiple models) filter. The experimental results on datasets collected from different scenarios such as: urban streets, country roads and highways demonstrate the efficiency of the proposed algorithm on a Daimler Mercedes demonstrator in the framework of the European Project PReVENT-ProFusion2.

Abstract: Recently, automatic parking assist systems have become commercially available in some cars. In order to improve the reliability and accuracy of parking control, pose estimation problem needs to be solved. Odometry is widely used for pose estimation of a mobile robot. However, most previous odometry calibration methods have focused on two wheeled mobile robots. In this paper, we consider systematic error sources of the car-like mobile robot(CLMR), and we suggest a useful calibration method for systematic errors. Finally, our calibration method is verified by experiments using a miniature car.

Abstract: We present a novel particle filter implementation for estimating the pose of tags in the environment with respect to an RFID-equipped robot. This particle filter combines signals from a specially designed RFID antenna system with odometry and an RFID signal propagation model. Our model includes antenna characteristics, direct-path RF propagation, and multipath RF propagation. We first describe a novel 6-antenna RFID sensor system that provides the robot with a 360-degree view of the tags in its environment. We then present the results of real-world evaluation where RFID-inferred tag position is compared with ground truth data from a laser range-finder. In our experiments the system is shown to estimate the pose of UHF RFID tags in a real-world environment without requiring a priori training or map-building. The system exhibits 6.1 deg mean bearing error and 0.69 m mean range error over robot to tag distances of over 4 m in an environment with significant multipath. The RFID system provides the ability to uniquely identify specific tagged locations and objects, and to discriminate among multiple tagged objects in the field at the same time, which are important capabilities that a laser range-finder does not provide. We expect that this new type of multiple-antenna RFID system, including particle filters that incorporate RF signal propagation models, will prove to be a valuable sensor for mobile robots operating in semi-structured environments where RFID tags are present.

Abstract: This paper introduces vision based loop closure detection in Simultaneous Localisation And Mapping (SLAM) using Tree of Words. The loop closure performance in a complex urban environment is examined and an additional feature is suggested for safer matching. A SLAM ground experiment in an urban area is performed using Tree of Words, a delayed state information filter and planar laser scans for relative pose estimation. Results show that a good map estimation using our vision based loop closure detection can be obtained in near real, yet constant, time. It is shown that an odometry supported recall rate of almost 70% can be obtained with a false detection rate of about 0.01%.

Abstract: Due to their omnidirectional view, the use of catadioptric cameras is of great interest for robot localization and visual servoing. For simplicity, most vision-based algorithms use image processing tools (e.g. image smoothing) that were designed for perspective cameras. This can be a good approximation when the camera displacement is small with respect to the distance to the observed environment. Otherwise, perspective image processing tools are unable to accurately handle the signal distortion that is induced by the specific geometry of omnidirectional cameras. In this paper, we propose an appropriate spherical image processing for increasing the accuracy of visual odometry estimation. The omnidirectional images are mapped onto a unit sphere and treated in the spherical spectral domain. The spherical image processing take into account the specific geometry of omnidirectional cameras. For example we can design, a more accurate and more repeatable Harris interest point detector. The interest points can be matched between two images with a large baseline in order to accurately estimate the camera motion. We demonstrate with a real experiment the accuracy of the visual odometry obtained using the spherical image processing and the improvement with respect to the use of a standard perspective image processing.

Abstract: This paper describes a method for estimating the vehicle global position in a network of roads by means of visual odometry. To do so, the ego-motion of the vehicle relative to the road is computed using a stereo-vision system mounted next to the rear view mirror of the car. Feature points are matched between pairs of frames and linked into 3D trajectories. Vehicle motion is estimated using the non-linear, photogrametric approach based on RANSAC. This iterative technique enables the formulation of a robust method that can ignore large numbers of outliers as encountered in real traffic scenes. The resulting method is defined as visual odometry and can be used in conjunction with other sensors, such as GPS, to produce accurate estimates of the vehicle global position. The obvious application of the method is to provide on-board driver assistance in navigation tasks, or to provide a means for autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene nor the vehicle motion. We provide examples of estimated vehicle trajectories using the proposed method and discuss the key issues for further improvement.

Abstract: A key problem in the deployment of sensor networks is that of determining the location of each sensor such that subsequent data gathered can be registered. We would also like the network to provide localization for mobile entities, allowing them to navigate and explore the environment. In this paper, we present a robust decentralized algorithm for mapping the nodes in a sparsely connected sensor network using range- only measurements and odometry from a mobile robot. Our approach utilizes an extended Kalman filter (EKF) in polar space allowing us to model the nonlinearities within the range-only measurements using Gaussian distributions. We also extend this unimodal centralized EKF to a multi-modal decentralized framework enabling us to accurately model the ambiguities in range-based position estimation. Each node within the network estimates its position along with its neighbor's position and uses a message-passing algorithm to propagate its belief to its neighbors. Thus, the global network localization problem is solved in pieces, by each node independently estimating its local network, greatly reducing the computation done by each node. We demonstrate the effectiveness of our approach using simulated and real-world experiments with little to no prior information about the node locations.

Abstract: An annotated data set is presented meant to help researchers in developing, evaluating, and comparing various approaches in robotics for building space representations appropriate for communicating with humans. The data consist of omnidirectional images, laser range scans, sonar readings, and robot odometry. A set of base-level human spatial concepts is used to annotate the data.

Abstract: Humanoids have recently become a popular research platform in the robotics community. Such robots offer various fields for new applications. However, they have several drawbacks compared to wheeled vehicles such as stability problems, limited payload capabilities, violation of the flat world assumption, and they typically provide only very rough odometry information, if at all. In this paper, we investigate the problem of learning accurate grid maps with humanoid robots. We present techniques to deal with some of the above-mentioned difficulties. We describe how an existing approach to the simultaneous localization and mapping (SLAM) problem can be adapted to robustly learn accurate maps with a humanoid equipped with a laser range finder. We present an experiment in which our mapping system builds a highly accurate map with a size of around 20 m by 20 m using data acquired with a humanoid in our office environment containing two loops. The resulting maps have a similar accuracy as maps built with a wheeled robot.

Abstract: This paper describes an improving method for solving localization problems with a highly accurate model of a mobile robot either in an uncertainly large-scale environment. Firstly, we motivate our approach by analyzing intensively the dead-reckoning model for the tricycle robot type. Secondly, we propose the localization algorithm based on a Hybrid Extended Kalman Filter using artificial beacons. In this paper, 360deg sensor scan is used for each observation and the odometry data is updated to estimate the robot position. Then a comparison between the real and the estimated location of beacons and analyzing of the filterpsilas performance are taken. The simulation results show that the proposed algorithm can lead the robot to robustly navigate in uncertain environments.

Abstract: A key problem of a mobile robot system is how to localize itself and detect objects in the workspace. In this paper, a multiple sensor based robot localization and object pose estimation method is presented. First, optical encoders and odometry model are utilized to determine the pose of the mobile robot in the workspace, with respect to the global coordinate system. Next, a CCD camera is used as a passive sensor to find an object (a box) in the environment, including the specific vertical surfaces of the box. By identifying and tracking color blobs which are attached to the center of each vertical surface of the box, the robot rotates and adjusts its base pose to move the color blob into the center of the camera view in order to make sure that the box is in the range of the laser scanner. Finally, a laser range finder, which is mounted on the top of the mobile robot, is activated to detect and compute the distances and angles between the laser source and laser contact surface on the box. Based on the information acquired in this manner, the global pose of the robot and the box can be represented using the homogeneous transformation matrix. This approach is validated using the Microsoft Robotics Studio simulation environment.

Abstract: This paper develops a novel automatic parking algorithm based on a fuzzy logic controller with the vehicle pose for the input and the steering rate for the output. It localizes the vehicle by using only external sensors - a vision sensor and ultrasonic sensors. Then it automatically learns an optimal fuzzy if-then rule set from the training data, using an evolutionary fuzzy system. Furthermore, it also finds the green zone for the ready-to-reverse position in which parking is possible just by reversing. It has been tested on a 4-wheeled Pioneer mobile robot which emulates the real vehicle.

Abstract: We present a method for calculating odome- try in three-dimensions for car-like ground ve- hicles with an Ackerman-like steering model. In our approach we use the information from a single camera to derive the odometry in the plane and fuse it with roll and pitch informa- tion derived from an on-board IMU to extend to three-dimensions, thus providing odometric altitude as well as traditional x and y transla- tion. We have mounted the odometry module on a standard Toyota Prado SUV and present results from a car-park environment as well as from an off-road track.

Abstract: Simultaneous Localisation and Mapping (SLAM) implementations are typically based upon integration of multiple sensors. One of the most common configurations for SLAM is the combination of odometry and range sensors. However, these sensors usually capture measurements at different times and thus introduce additional time synchronisation error when their data are fused together directly. As a robot moves faster, this error becomes more significant. The overall aim is to allow the robot to travel quickly and yet still be capable of obtaining accurate localisation and mapping results. This paper presents techniques for time synchronisation of multiple sensors taking into account clock drifts, inaccuracy of timestamps, and other unexpected communication and operating system delays. This paper also introduces a method of calibrating odometry and range sensors to ensure an accurate data fusion. Experimental results with and without synchronisation are shown to illustrate and validate the improvements.

Abstract: A robotic device is manually driven along a perimeter of a Region Of Interest (ROI) or along a Path Of Interest (POI) for future autonomous operation. An Initial Point (IP) is established by identifying a unique machine recognizable feature, for example, a Radio Frequency Identification (RFID) tag located at the IP. The robotic device is then manually driven along the perimeter or along the path and sensors carried by the robotic device collects data to characterize the ROI or POI. The sensors may include sonar, vision systems, laser, or radar devices for measuring relative positions of a wall, stairs, or obstacles. Wheel odometry may be used to track distances traveled and data fusion exercised to combine the odometry data with the sonar and/or laser measurements to model the ROI or POI. Characterization is performed by collecting points along a wall, fitting a line to the points, and finding the intersections of consecutive lines.

Abstract: It is a key issue for mobile robot navigation to have the ability of accurate and reliable dead reckoning. Aimed at this issue, dead reckoning of mobile robot in complex terrain is analyzed by the rigid-body kinematic constraints of mobile robot. At the same time, the kinematic model of mobile robot is obtained using multiple proprioceptive sensorspsila information from odometry, fiber optic gyro, tilt sensor, et al. A method of kinematic model integrated with wheel-ground contact angle is suggested to estimate the relative motion trajectory of mobile robot. Experimental results obtained in simulation and with real robot on different terrains demonstrate that this method is more close to real pose of mobile robot than to calculate only with the pitch.

Abstract: Robustness is pivot for robots operating in all-terrain environments. This demand comes mainly due to the highly heterogeneous and unstructured nature of the terrain. Two particular topics are sensitive to this problem: locomotion control and wheel odometry. A behaviour-based approach is proposed for the locomotion control system, whereas a heuristic exploiting the kinematic and dynamical constraints of the robot is used to enhance wheel odometry accuracy. Experimental results on the Ares robot, which is a \(1.5\,\mbox{m}^2\) vehicle with four independently steered wheels, show the ability of the proposed methods to cope with all-terrain environments. In addition, the modules for localisation, mapping, and obstacle avoidance are also addressed in order to provide a global perspective over the Ares robot’s control system.

Abstract: This paper describes a new approach for estimating the vehicle motion trajectory in complex urban environments by means of visual odometry. A new strategy for robust feature extraction and data post-processing is developed and tested on-road. Scale-invariant Image Features (SIFT) are used in order to cope with the complexity of urban environments. The obtained results are discussed and compared to previous works. In the prototype system, the ego-motion of the vehicle is computed using a stereo-vision system mounted next to the rear view mirror of the car. Feature points are matched between pairs of frames and linked into 3D trajectories. The distance between estimations is dynamically adapted based on reprojection and estimation errors. Vehicle motion is estimated using the non-linear, photogrametric approach based on RANSAC (RAndom SAmple Consensus). The obvious application of the method is to provide on-board driver assistance in navigation tasks, or to provide a means of autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene or the vehicle motion. An example of how to estimate a vehiclepsilas trajectory is provided along with suggestions for possible further improvement of the proposed odometry algorithm.

Abstract: In this paper we present a novel approach to legged humanoid navigation on indoor environments using classical probabilistic SLAM methods based on odometry information and laser measurements. We use two small lasers installed in the robot feet to capture distance data. Odometry is obtained by calculating the position of each laser-foot at every time step. The SLAM problem is solved by using a multi-laser SLAM solution together with a holonomic motion model. Navigation skills also include a path planning module with obstacle avoidance for autonomous navigation in indoor environments. The whole process is performed within the robot itself. Optionally, localization robustness is increased by adding the detection of landmarks using a camera. Results obtained are presented for the 1.5 m tall Reem-B humanoid robot.

Abstract: This paper describes a robust localization system, similar to the used by the teams participating in the Robocup Small size league (SLL). The system, developed in Object Pascal, allows real-time localization and control of an autonomous omnidirectional mobile robot. The localization algorithm is done resorting to odometry and global vision data fusion, applying an extended Kalman filter.