Robot Localization based on Geo-referenced Images and G raphic Methods

Size: px
Start display at page:

Download "Robot Localization based on Geo-referenced Images and G raphic Methods"

Transcription

1 Robot Localization based on Geo-referenced Images and G raphic Methods Sid Ahmed Berrabah Mechanical Department, Royal Military School, Belgium, sidahmed.berrabah@rma.ac.be Janusz Bedkowski, Łukasz Lubasiński, Andrzej Masłowski Research Institute for Automation and Measurements, PIAP, Poland, januszbedkowski@gmail.com Abstract This paper describes tow methods for Simultaneous Localization and Mapping for mobile robot navigation in outdoor and indoor environments. The first method is a feature-based algorithm which combines geo-referenced images in order to localize the robot in a user defined global coordinate frame and keep track of all detected landmarks (features). This method builds a map of the environment using an history memory which accumulates sensory evidence over time to identify places with a stochastic model of the correlation between map features, and then, integrates data from GPS to localize the built map and therefore the robot in geo-referenced images. The user can then communicate with the robot to define a final goal (target) using only the geo-referenced images. The second method is a graphics based approach. It encloses set of graphic methods to obtain robot translation and rotation according to global map. The idea is based on the comparison of the match scan, therefore the translation and rotation between 2 scan is obtained. The algorithm is implemented using OpenGL (Open Graphic Library) technology in CORBA (Common Object Request Broker Architecture). This method is well suited for indoor navigation. I. Introduction Industrial growth of nowadays makes it necessary to replace humans working in assembly lines by accurate and rapid robots. Current industrial robots lack flexibility and autonomy and are not able to operate in new environments. That is why, autonomous mobile robots are required. Autonomous robotics aim is the control of the motion of a mobile robot to navigate from a start point to an end point based on the description of the workspace given by the sensors. To reach a reasonable degree of autonomy, two basic requirements are sensing and reasoning. Sensing is provided by an on board sensory system that gather information about the robot it self and the surrounding environment. Reasoning is accomplished by developing algorithms that exploit this information in order to generate appropriate commands for the robot. The reasoning system is the central unit in an autonomous robot. According to the environment state, it must allow the robot to localize itself in the environment and to seek for free paths. To accomplish these

2 two tasks, it bases its reasoning on a model or a description of the environment, but this model is not always available and in this case the robot should have the means to build such a model over time as it explores its environments. This latest problem is known as mapping problem. Mapping and localization are interlinked problems: without a precise map, the robot cannot localize itself using the map. On the other hand, without precise knowledge of its pose (spatial position and orientation), the robot cannot build a representation of its environment. In combination, however, the problem is much harder. In this case, starting from an unknown location in an unknown environment, an autonomous mobile robot should be able to incrementally build a map of the environment using only relative observations of the environment and then use this map to localize itself and navigate. This is the so-called simultaneous localization and mapping (SLAM) approach. In this paper, we present two methods to solve the SLAM problem for outdoor and indoor environments. The first method is a vision-based SLAM where a single camera is used by the outdoor robot ROBUDEM of the Royal Military School to build a model of the scene and localize the robot. This is interesting because it offers a low-cost and real-time approach to SLAM in unprepared environments. The camera identifies natural features in the scene and uses these as landmarks in the built map. To model large environments, the proposed approach builds several size limited local maps and combines them in a global one. The proposed method uses an 'history memory' which accumulates sensory evidence over time to identify places with a stochastic model of the correlation between map features. This helps also to overcome the problem of perceptual aliasing, which refers to situations where several places are perceptually similar enough to be confused by the robot. Using data from GPS, the built map is superposed to geo-referenced images allowing therefore the localization of the robot in a user defined global frame. In the second approach proposed, an indoor mobile robot ATRV-JR (PIAP) uses a laser sick range finder to model the environment as an occupancy grid map. The localization of the robot is done by matching the laser scans. The rest of the paper is organized as follows: the proposed approaches are described in details in sections II and III, followed by conclusions in section IV. II. Vision-based Simultaneous Localization and Mapping In the Outdoor application the robot ROBUDEM uses a single monocular camera to extract natural features in the scene. These features are used as landmarks in the built map. The SLAM problem is tackled as a stochastic problem using an Extended Kalman Filtering to maintain the state vector, x, consisting of the robot state, x R, and map feature states, x Li. It also maintains a covariance matrix, P, which includes the uncertainties in the various states as well as correlations between the states. Feature states x Li are the 3D position vectors of the locations of feature points. The (robot) camera state vector x R comprises [] a metric 3D position vector r W, orientation quaternion q RW, velocity vector v W, and angular velocity vector w R relative to a fixed world frame W and robot frame R:

3 Features are image patches with a size of x pixels. The patches are supposed locally as planar surfaces perpendicular to the vector from the feature to the camera at initialization. When making measurements of a feature from new camera positions, each patch can be projected from 3D to the image plane to produce a template for matching with the real image. This template will be a warped version of the original square template captured when the feature was first detected. To avoid using outlier features, the moving object mask detected by the motion segmentation procedure introduced in [2] is used. Subsequently, during map building, the detected features on the moving parts are excluded. The coordinate frame is chosen at the starting position and the system is helped at the beginning with an amount of prior information about the scene. A shape of a known target is placed in front of the camera, which provides several features with known positions and known appearance. This will help to know the scaling of the estimated map and an initialization of the map as with only a single camera, the features cannot be initialized on the map based only on one measurement because of their unknown depth. The system starts with zero uncertainty. Feature matching is carried out using straightforward normalization cross-correlation search for the template patch projected into the current camera estimate. The image is scanned at each location until a match is found. This searching for match is computationally expensive. A feature-based SLAM algorithm using Extended Kalman Filtering has two important limitations when mapping large environments. First, the computational cost of updating the map grows with O(N 2 ) (N is the number of features + size of the robot state). Second, as the map grows, the estimates obtained by the EKF equations quickly become inconsistent due to linearization errors [3]. To overcome these limitations, the proposed approach builds small independent local maps of limited size and joins them in global one. Each local map is represented by a separate Extended Kalman Filter. For joining local maps we use a 'history memory' which accumulates sensory evidence over time to identify places with a stochastic model of the correlation between map features to obtain one full stochastic map. This is done by transforming each local map into a global frame before to start building a new local map. The base frame for the global map is the robot position at instant x R t. Local maps are built as follows: at a given instant t k, a new map is initialized using the current vehicle location, x R tk,as base reference B i = x R tk, where i=, 2,..., is the local map order. Then, the vehicle performs a limited motion acquiring sensor information about the neighboring environment features L i. Where is the coordinate vector in the base reference B i of the L i detected features and covariance matrix estimated in B i. The robot decides to start a new local map when the number of mapped features reaches a predefined threshold. Each finalized local map is then transferred to the global map before starting a new one, by computing the state vectors and the covariance matrix. The coordinate frame of the first local map is used as the coordinate frame of the global map:

4 Where is a concatenation of all features from local maps,, 2, : The covariance transition function. of the joint map is obtained from the linearization of the state The obtained map can be superimposed to a satellite image of the navigated area by matching the GPS data corresponding to frame coordinates of the local maps. III. graphic based Simultaneous Localization and Mapping In the indoor ATRV application, the method uses a laser range finder to build an occupancy grid map of an indoor navigation area. The localization of the robot is obtained by matching the laser scans. The measurement is acquired using LMS SICK 22 range finder. Sick LMS 22 reads data every.5 (-9 ;9 ). It gives 36 points. Data from laser is obtained in the polar coordinate system (r i, α i ) where: r i distance to an obstacle [meters], α i the horizontal angle (figure ) Figure. LSM SICK 2, and its scanning angle. They are recalculated to Cartesian one, by the following equations: x i = r i cos(α) y i = ; () z i = r i sin(α) where: (x i, y i, z i ) Cartesian coordinate of a point. Data is collected into vector R = [r, r 2, r i ] The vector R is transformed into set {( x i, y i, z i )} i =, n using equation (). The laser data is a result of intersection of scanning plane and obstacles planes. The computed set of points is merged into the lines, and rendered in OpenGL window ( figure 4 scan). The idea if presented method is to find transformation matrix M which transform scan t into scan t 2 (where t time of collected first scan, t 2 time of collected second scan).

5 Therefore we can compute new location of robot P new (x new, y new, z new ). P new = P old M (2) where P old position of robot in t The idea of the localization algorithm is based on the match 2 laser scans. The robot motion is defined as translation and rotation. Therefore it is possible to predict the robot position estimation in the rectangle shown in figure 2. Each element from matrix of the translation contains the table of rotation angles. Multiplying translation matrix and rotation matrix gives estimated robot position matrix. The goal is to compute an appropriate combination of the translation and rotation matrix accordingly, to maximizing the similarity of the 2 laser scans. The similarity is described by the amount of scan pixels (figure 4). Figure 2: Robot position estimation in the rectangle described by matrix of translation. The algorithm is composed by 2 elements: initialization and main match scan procedure. The pseudo code of initialization is given: Init() { For i = i < SIZE_TABLE_O F_X_INDEXES_O F_TRANSLATION_MATRIX i+ + For j = j < SIZE_TABLE_O F_Z_INDEXES_O F_TRANSLATION_MATRIX j+ + For k = k < SIZE_TABLE_O F_ROTATION_ANGLES k+ + M[i][j][k] = BuildTransformationMatrix(i, j, k) return; } The BuildTransformationMatrix procedure obtains the translation matrix from values of translation dx in X axis and dz in Z axis and rotation matrix from rotation angle α. The matrixes M xz and M α are given:

6 cos sin M xz M sin cos dx dz The result of the BuildTransformationMatrix is the set of matrixes M i which are involved into computing new location of robot P new i (x new, y new, z new ). P new i = P old M i (3) The MatchScan procedure uses opengl 256 x 256 pixels window. The example of rendering the LSM SICK22 scan is shown on fugure 3: Figure 3: OpenGL window with rendered LSM SICK 22 scan; MatchScan() { Load(Scan); Load(Scan2); For i = i < SIZE_TABLE_O F_X_INDEXES_O F_TRANSLATION_MATRIX i+ + For j = j < SIZE_TABLE_O F_Z_INDEXES_O F_TRANSLATION_MATRIX j+ + For k = k < SIZE_TABLE_O F_ROTATION_ANGLES k+ + { ClearOpenGLWindow(); Render(Scan); Transform(Scan2, M[i][j][k]); Render(Scan2); CountNumberOfScanPixels; //scans are rendered using different //color than background If numberofscanpixels < minnumberofscanpixels

7 { minnumberofscanpixels = numberofscanpixels; } } return i, j, k for minnumberofscanpixels; } The following figure shows an idea of the opengl graphic library usage in the matchscan procedure. Figure 4: Example of 2 situations in matchscan procedure. Left one represents correct matching, due to the number of non white pixels in the left image is smaller than in the right image. Therefore the second image represents a wrong match. III.. Result using the second method The following section presents an experimental evaluation of localization algorithm based on 2D laser scans for indoor environment. Experiments are performed on real scans collected in an office environment with a map size of m x 2m. The algorithm of the robot localization based on graphic methods is presented. Experiments were executed on the PC with dual core processor with 2GB of ram and NVIDIA GEFORCE 76 graphic card. The goal of serving the precise position estimation is achieved. The result of the presented procedures is shown on figure 5:

8 Figure 5: The result of the matchscan procedure: red color describes the reconstructed map, blue line describes robot s path, and green rectangle shows the current robot position. I V. Conclusion We presented two methods for simultaneous Localization and Mapping for mobile robot navigation in indoor and outdoor environment. The first method is a vision-based approach for the Outdoor ROBUDEM application, which identifies natural features in the scene and uses these as landmarks. The algorithm builds several size limited local maps and merge them in a global map using an history memory. The built map can then be superimposed to a geo-referenced image of the navigated area using GPS data at the local map coordinate frames. In the second approach, the indoor robot CTRV-JR uses a laser range finder to build an occupancy grid map of an its navigation area. The localization of the robot is obtained by matching the laser scans. Acknowledgment: This research is founded by the View-Finder FP6 IST 4554 project. V. References [] A. J. Davison, I. D. Reid, N. D. Molton, O. Stasse, MonoSLAM: Real-Time Single Camera SLAM, IEEE Trans. PAMI 27. [2] S.A. Berrabah, G. De Cubber, V. Enescu, H. Sahli, MRF-Based Foreground Detection in Image Sequences from a Moving Camera, IEEE International Conference on Image Processing (ICIP 26), Atlanta, GA, USA, Oct. 26, pp.25-28, [3] J.D. Trados, J. Neira, P. Newman, J. Leonard, Robust mapping and localization in indoor environments using sonar data, International Journal of Robotics Research, 22, N. 2, pp.3-33.

SLAM for Robotic Assistance to fire-fighting services

SLAM for Robotic Assistance to fire-fighting services SLAM for Robotic Assistance to fire-fighting services Sid Ahmed Berrabah *,**, Yvan Baudoin *, Hichem Sahli ** * Royal Military Academy of Belgium (RMA), Av. de la Renaissance 30, B1000 Brussels, Belgium

More information

Robotics. Lecture 7: Simultaneous Localisation and Mapping (SLAM)

Robotics. Lecture 7: Simultaneous Localisation and Mapping (SLAM) Robotics Lecture 7: Simultaneous Localisation and Mapping (SLAM) See course website http://www.doc.ic.ac.uk/~ajd/robotics/ for up to date information. Andrew Davison Department of Computing Imperial College

More information

Augmented Reality, Advanced SLAM, Applications

Augmented Reality, Advanced SLAM, Applications Augmented Reality, Advanced SLAM, Applications Prof. Didier Stricker & Dr. Alain Pagani alain.pagani@dfki.de Lecture 3D Computer Vision AR, SLAM, Applications 1 Introduction Previous lectures: Basics (camera,

More information

Segmentation and Tracking of Partial Planar Templates

Segmentation and Tracking of Partial Planar Templates Segmentation and Tracking of Partial Planar Templates Abdelsalam Masoud William Hoff Colorado School of Mines Colorado School of Mines Golden, CO 800 Golden, CO 800 amasoud@mines.edu whoff@mines.edu Abstract

More information

CSE 527: Introduction to Computer Vision

CSE 527: Introduction to Computer Vision CSE 527: Introduction to Computer Vision Week 10 Class 2: Visual Odometry November 2nd, 2017 Today Visual Odometry Intro Algorithm SLAM Visual Odometry Input Output Images, Video Camera trajectory, motion

More information

Autonomous Mobile Robot Design

Autonomous Mobile Robot Design Autonomous Mobile Robot Design Topic: EKF-based SLAM Dr. Kostas Alexis (CSE) These slides have partially relied on the course of C. Stachniss, Robot Mapping - WS 2013/14 Autonomous Robot Challenges Where

More information

VIEW-FINDER : Robotics Assistance to fire-fighting services

VIEW-FINDER : Robotics Assistance to fire-fighting services VIEW-FINDER : Robotics Assistance to fire-fighting services Y. Baudoin, D. Doroftei, G. De Cubber, S.A. Berrabah, E. Colon, C. Pinzon Royal Military Academy, Polytechnics 30 Av de la Renaissance, 1000

More information

MAPPING ALGORITHM FOR AUTONOMOUS NAVIGATION OF LAWN MOWER USING SICK LASER

MAPPING ALGORITHM FOR AUTONOMOUS NAVIGATION OF LAWN MOWER USING SICK LASER MAPPING ALGORITHM FOR AUTONOMOUS NAVIGATION OF LAWN MOWER USING SICK LASER A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Engineering By SHASHIDHAR

More information

Simulation of a mobile robot with a LRF in a 2D environment and map building

Simulation of a mobile robot with a LRF in a 2D environment and map building Simulation of a mobile robot with a LRF in a 2D environment and map building Teslić L. 1, Klančar G. 2, and Škrjanc I. 3 1 Faculty of Electrical Engineering, University of Ljubljana, Tržaška 25, 1000 Ljubljana,

More information

LOAM: LiDAR Odometry and Mapping in Real Time

LOAM: LiDAR Odometry and Mapping in Real Time LOAM: LiDAR Odometry and Mapping in Real Time Aayush Dwivedi (14006), Akshay Sharma (14062), Mandeep Singh (14363) Indian Institute of Technology Kanpur 1 Abstract This project deals with online simultaneous

More information

Exam in DD2426 Robotics and Autonomous Systems

Exam in DD2426 Robotics and Autonomous Systems Exam in DD2426 Robotics and Autonomous Systems Lecturer: Patric Jensfelt KTH, March 16, 2010, 9-12 No aids are allowed on the exam, i.e. no notes, no books, no calculators, etc. You need a minimum of 20

More information

Geometrical Feature Extraction Using 2D Range Scanner

Geometrical Feature Extraction Using 2D Range Scanner Geometrical Feature Extraction Using 2D Range Scanner Sen Zhang Lihua Xie Martin Adams Fan Tang BLK S2, School of Electrical and Electronic Engineering Nanyang Technological University, Singapore 639798

More information

Simuntaneous Localisation and Mapping with a Single Camera. Abhishek Aneja and Zhichao Chen

Simuntaneous Localisation and Mapping with a Single Camera. Abhishek Aneja and Zhichao Chen Simuntaneous Localisation and Mapping with a Single Camera Abhishek Aneja and Zhichao Chen 3 December, Simuntaneous Localisation and Mapping with asinglecamera 1 Abstract Image reconstruction is common

More information

Mobile Robotics. Mathematics, Models, and Methods. HI Cambridge. Alonzo Kelly. Carnegie Mellon University UNIVERSITY PRESS

Mobile Robotics. Mathematics, Models, and Methods. HI Cambridge. Alonzo Kelly. Carnegie Mellon University UNIVERSITY PRESS Mobile Robotics Mathematics, Models, and Methods Alonzo Kelly Carnegie Mellon University HI Cambridge UNIVERSITY PRESS Contents Preface page xiii 1 Introduction 1 1.1 Applications of Mobile Robots 2 1.2

More information

Monocular SLAM for a Small-Size Humanoid Robot

Monocular SLAM for a Small-Size Humanoid Robot Tamkang Journal of Science and Engineering, Vol. 14, No. 2, pp. 123 129 (2011) 123 Monocular SLAM for a Small-Size Humanoid Robot Yin-Tien Wang*, Duen-Yan Hung and Sheng-Hsien Cheng Department of Mechanical

More information

Data Association for SLAM

Data Association for SLAM CALIFORNIA INSTITUTE OF TECHNOLOGY ME/CS 132a, Winter 2011 Lab #2 Due: Mar 10th, 2011 Part I Data Association for SLAM 1 Introduction For this part, you will experiment with a simulation of an EKF SLAM

More information

Indoor Positioning System Based on Distributed Camera Sensor Networks for Mobile Robot

Indoor Positioning System Based on Distributed Camera Sensor Networks for Mobile Robot Indoor Positioning System Based on Distributed Camera Sensor Networks for Mobile Robot Yonghoon Ji 1, Atsushi Yamashita 1, and Hajime Asama 1 School of Engineering, The University of Tokyo, Japan, t{ji,

More information

Vehicle Localization. Hannah Rae Kerner 21 April 2015

Vehicle Localization. Hannah Rae Kerner 21 April 2015 Vehicle Localization Hannah Rae Kerner 21 April 2015 Spotted in Mtn View: Google Car Why precision localization? in order for a robot to follow a road, it needs to know where the road is to stay in a particular

More information

Monocular SLAM with Inverse Scaling Parametrization

Monocular SLAM with Inverse Scaling Parametrization Monocular SLAM with Inverse Scaling Parametrization D. Marzorati 2, M. Matteucci 1, D. Migliore 1, and D. G. Sorrenti 2 1 Dept. Electronics and Information, Politecnico di Milano 2 Dept. Informatica, Sistem.

More information

Visual Bearing-Only Simultaneous Localization and Mapping with Improved Feature Matching

Visual Bearing-Only Simultaneous Localization and Mapping with Improved Feature Matching Visual Bearing-Only Simultaneous Localization and Mapping with Improved Feature Matching Hauke Strasdat, Cyrill Stachniss, Maren Bennewitz, and Wolfram Burgard Computer Science Institute, University of

More information

Intelligent Outdoor Navigation of a Mobile Robot Platform Using a Low Cost High Precision RTK-GPS and Obstacle Avoidance System

Intelligent Outdoor Navigation of a Mobile Robot Platform Using a Low Cost High Precision RTK-GPS and Obstacle Avoidance System Intelligent Outdoor Navigation of a Mobile Robot Platform Using a Low Cost High Precision RTK-GPS and Obstacle Avoidance System Under supervision of: Prof. Dr. -Ing. Klaus-Dieter Kuhnert Dipl.-Inform.

More information

Optimization of the Simultaneous Localization and Map-Building Algorithm for Real-Time Implementation

Optimization of the Simultaneous Localization and Map-Building Algorithm for Real-Time Implementation 242 IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 17, NO. 3, JUNE 2001 Optimization of the Simultaneous Localization and Map-Building Algorithm for Real-Time Implementation José E. Guivant and Eduardo

More information

AR Cultural Heritage Reconstruction Based on Feature Landmark Database Constructed by Using Omnidirectional Range Sensor

AR Cultural Heritage Reconstruction Based on Feature Landmark Database Constructed by Using Omnidirectional Range Sensor AR Cultural Heritage Reconstruction Based on Feature Landmark Database Constructed by Using Omnidirectional Range Sensor Takafumi Taketomi, Tomokazu Sato, and Naokazu Yokoya Graduate School of Information

More information

L12. EKF-SLAM: PART II. NA568 Mobile Robotics: Methods & Algorithms

L12. EKF-SLAM: PART II. NA568 Mobile Robotics: Methods & Algorithms L12. EKF-SLAM: PART II NA568 Mobile Robotics: Methods & Algorithms Today s Lecture Feature-based EKF-SLAM Review Data Association Configuration Space Incremental ML (i.e., Nearest Neighbor) Joint Compatibility

More information

Localization and Map Building

Localization and Map Building Localization and Map Building Noise and aliasing; odometric position estimation To localize or not to localize Belief representation Map representation Probabilistic map-based localization Other examples

More information

HOG-Based Person Following and Autonomous Returning Using Generated Map by Mobile Robot Equipped with Camera and Laser Range Finder

HOG-Based Person Following and Autonomous Returning Using Generated Map by Mobile Robot Equipped with Camera and Laser Range Finder HOG-Based Person Following and Autonomous Returning Using Generated Map by Mobile Robot Equipped with Camera and Laser Range Finder Masashi Awai, Takahito Shimizu and Toru Kaneko Department of Mechanical

More information

6 y [m] y [m] x [m] x [m]

6 y [m] y [m] x [m] x [m] An Error Detection Model for Ultrasonic Sensor Evaluation on Autonomous Mobile Systems D. Bank Research Institute for Applied Knowledge Processing (FAW) Helmholtzstr. D-898 Ulm, Germany Email: bank@faw.uni-ulm.de

More information

Robotic Mapping. Outline. Introduction (Tom)

Robotic Mapping. Outline. Introduction (Tom) Outline Robotic Mapping 6.834 Student Lecture Itamar Kahn, Thomas Lin, Yuval Mazor Introduction (Tom) Kalman Filtering (Itamar) J.J. Leonard and H.J.S. Feder. A computationally efficient method for large-scale

More information

Dense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm

Dense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm Computer Vision Group Prof. Daniel Cremers Dense Tracking and Mapping for Autonomous Quadrocopters Jürgen Sturm Joint work with Frank Steinbrücker, Jakob Engel, Christian Kerl, Erik Bylow, and Daniel Cremers

More information

Estimation of Planar Surfaces in Noisy Range Images for the RoboCup Rescue Competition

Estimation of Planar Surfaces in Noisy Range Images for the RoboCup Rescue Competition Estimation of Planar Surfaces in Noisy Range Images for the RoboCup Rescue Competition Johannes Pellenz pellenz@uni-koblenz.de with Sarah Steinmetz and Dietrich Paulus Working Group Active Vision University

More information

Revising Stereo Vision Maps in Particle Filter Based SLAM using Localisation Confidence and Sample History

Revising Stereo Vision Maps in Particle Filter Based SLAM using Localisation Confidence and Sample History Revising Stereo Vision Maps in Particle Filter Based SLAM using Localisation Confidence and Sample History Simon Thompson and Satoshi Kagami Digital Human Research Center National Institute of Advanced

More information

Motion estimation of unmanned marine vehicles Massimo Caccia

Motion estimation of unmanned marine vehicles Massimo Caccia Motion estimation of unmanned marine vehicles Massimo Caccia Consiglio Nazionale delle Ricerche Istituto di Studi sui Sistemi Intelligenti per l Automazione Via Amendola 122 D/O, 70126, Bari, Italy massimo.caccia@ge.issia.cnr.it

More information

W4. Perception & Situation Awareness & Decision making

W4. Perception & Situation Awareness & Decision making W4. Perception & Situation Awareness & Decision making Robot Perception for Dynamic environments: Outline & DP-Grids concept Dynamic Probabilistic Grids Bayesian Occupancy Filter concept Dynamic Probabilistic

More information

COMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION

COMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION COMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION Mr.V.SRINIVASA RAO 1 Prof.A.SATYA KALYAN 2 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING PRASAD V POTLURI SIDDHARTHA

More information

Navigation methods and systems

Navigation methods and systems Navigation methods and systems Navigare necesse est Content: Navigation of mobile robots a short overview Maps Motion Planning SLAM (Simultaneous Localization and Mapping) Navigation of mobile robots a

More information

EE565:Mobile Robotics Lecture 3

EE565:Mobile Robotics Lecture 3 EE565:Mobile Robotics Lecture 3 Welcome Dr. Ahmad Kamal Nasir Today s Objectives Motion Models Velocity based model (Dead-Reckoning) Odometry based model (Wheel Encoders) Sensor Models Beam model of range

More information

INDOOR NAVIGATION BY USING SEGMENTATION OF RANGE IMAGES OBTAINED BY LASER SCANNERS

INDOOR NAVIGATION BY USING SEGMENTATION OF RANGE IMAGES OBTAINED BY LASER SCANNERS INDOOR NAVIGATION BY USING SEGMENTATION OF RANGE IMAGES OBTAINED BY LASER SCANNERS B. Gorte a, K. Khoshelham a, E. Verbree b a Optical and Laser Remote Sensing, Delft University of Technology, The Netherlands

More information

NAVIGATION SYSTEM OF AN OUTDOOR SERVICE ROBOT WITH HYBRID LOCOMOTION SYSTEM

NAVIGATION SYSTEM OF AN OUTDOOR SERVICE ROBOT WITH HYBRID LOCOMOTION SYSTEM NAVIGATION SYSTEM OF AN OUTDOOR SERVICE ROBOT WITH HYBRID LOCOMOTION SYSTEM Jorma Selkäinaho, Aarne Halme and Janne Paanajärvi Automation Technology Laboratory, Helsinki University of Technology, Espoo,

More information

ECE276A: Sensing & Estimation in Robotics Lecture 11: Simultaneous Localization and Mapping using a Particle Filter

ECE276A: Sensing & Estimation in Robotics Lecture 11: Simultaneous Localization and Mapping using a Particle Filter ECE276A: Sensing & Estimation in Robotics Lecture 11: Simultaneous Localization and Mapping using a Particle Filter Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Siwei Guo: s9guo@eng.ucsd.edu

More information

Integrated Laser-Camera Sensor for the Detection and Localization of Landmarks for Robotic Applications

Integrated Laser-Camera Sensor for the Detection and Localization of Landmarks for Robotic Applications 28 IEEE International Conference on Robotics and Automation Pasadena, CA, USA, May 19-23, 28 Integrated Laser-Camera Sensor for the Detection and Localization of Landmarks for Robotic Applications Dilan

More information

Mini Survey Paper (Robotic Mapping) Ryan Hamor CPRE 583 September 2011

Mini Survey Paper (Robotic Mapping) Ryan Hamor CPRE 583 September 2011 Mini Survey Paper (Robotic Mapping) Ryan Hamor CPRE 583 September 2011 Introduction The goal of this survey paper is to examine the field of robotic mapping and the use of FPGAs in various implementations.

More information

Roadmaps. Vertex Visibility Graph. Reduced visibility graph, i.e., not including segments that extend into obstacles on either side.

Roadmaps. Vertex Visibility Graph. Reduced visibility graph, i.e., not including segments that extend into obstacles on either side. Roadmaps Vertex Visibility Graph Full visibility graph Reduced visibility graph, i.e., not including segments that extend into obstacles on either side. (but keeping endpoints roads) what else might we

More information

Estimating Geospatial Trajectory of a Moving Camera

Estimating Geospatial Trajectory of a Moving Camera Estimating Geospatial Trajectory of a Moving Camera Asaad Hakeem 1, Roberto Vezzani 2, Mubarak Shah 1, Rita Cucchiara 2 1 School of Electrical Engineering and Computer Science, University of Central Florida,

More information

CS4758: Rovio Augmented Vision Mapping Project

CS4758: Rovio Augmented Vision Mapping Project CS4758: Rovio Augmented Vision Mapping Project Sam Fladung, James Mwaura Abstract The goal of this project is to use the Rovio to create a 2D map of its environment using a camera and a fixed laser pointer

More information

Simultaneous Localization and Mapping (SLAM)

Simultaneous Localization and Mapping (SLAM) Simultaneous Localization and Mapping (SLAM) RSS Lecture 16 April 8, 2013 Prof. Teller Text: Siegwart and Nourbakhsh S. 5.8 SLAM Problem Statement Inputs: No external coordinate reference Time series of

More information

EE631 Cooperating Autonomous Mobile Robots

EE631 Cooperating Autonomous Mobile Robots EE631 Cooperating Autonomous Mobile Robots Lecture: Multi-Robot Motion Planning Prof. Yi Guo ECE Department Plan Introduction Premises and Problem Statement A Multi-Robot Motion Planning Algorithm Implementation

More information

Real-Time Model-Based SLAM Using Line Segments

Real-Time Model-Based SLAM Using Line Segments Real-Time Model-Based SLAM Using Line Segments Andrew P. Gee and Walterio Mayol-Cuevas Department of Computer Science, University of Bristol, UK {gee,mayol}@cs.bris.ac.uk Abstract. Existing monocular vision-based

More information

arxiv: v1 [cs.cv] 18 Sep 2017

arxiv: v1 [cs.cv] 18 Sep 2017 Direct Pose Estimation with a Monocular Camera Darius Burschka and Elmar Mair arxiv:1709.05815v1 [cs.cv] 18 Sep 2017 Department of Informatics Technische Universität München, Germany {burschka elmar.mair}@mytum.de

More information

(W: 12:05-1:50, 50-N202)

(W: 12:05-1:50, 50-N202) 2016 School of Information Technology and Electrical Engineering at the University of Queensland Schedule of Events Week Date Lecture (W: 12:05-1:50, 50-N202) 1 27-Jul Introduction 2 Representing Position

More information

Real-time Obstacle Avoidance and Mapping for AUVs Operating in Complex Environments

Real-time Obstacle Avoidance and Mapping for AUVs Operating in Complex Environments Real-time Obstacle Avoidance and Mapping for AUVs Operating in Complex Environments Jacques C. Leedekerken, John J. Leonard, Michael C. Bosse, and Arjuna Balasuriya Massachusetts Institute of Technology

More information

Vision-based Mobile Robot Localization and Mapping using Scale-Invariant Features

Vision-based Mobile Robot Localization and Mapping using Scale-Invariant Features Vision-based Mobile Robot Localization and Mapping using Scale-Invariant Features Stephen Se, David Lowe, Jim Little Department of Computer Science University of British Columbia Presented by Adam Bickett

More information

Integrated Sensing Framework for 3D Mapping in Outdoor Navigation

Integrated Sensing Framework for 3D Mapping in Outdoor Navigation Integrated Sensing Framework for 3D Mapping in Outdoor Navigation R. Katz, N. Melkumyan, J. Guivant, T. Bailey, J. Nieto and E. Nebot ARC Centre of Excellence for Autonomous Systems Australian Centre for

More information

Large-Scale Robotic SLAM through Visual Mapping

Large-Scale Robotic SLAM through Visual Mapping Large-Scale Robotic SLAM through Visual Mapping Christof Hoppe, Kathrin Pirker, Matthias Ru ther and Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology, Austria {hoppe,

More information

High Accuracy Navigation Using Laser Range Sensors in Outdoor Applications

High Accuracy Navigation Using Laser Range Sensors in Outdoor Applications Proceedings of the 2000 IEEE International Conference on Robotics & Automation San Francisco, CA April 2000 High Accuracy Navigation Using Laser Range Sensors in Outdoor Applications Jose Guivant, Eduardo

More information

Stable Vision-Aided Navigation for Large-Area Augmented Reality

Stable Vision-Aided Navigation for Large-Area Augmented Reality Stable Vision-Aided Navigation for Large-Area Augmented Reality Taragay Oskiper, Han-Pang Chiu, Zhiwei Zhu Supun Samarasekera, Rakesh Teddy Kumar Vision and Robotics Laboratory SRI-International Sarnoff,

More information

L15. POSE-GRAPH SLAM. NA568 Mobile Robotics: Methods & Algorithms

L15. POSE-GRAPH SLAM. NA568 Mobile Robotics: Methods & Algorithms L15. POSE-GRAPH SLAM NA568 Mobile Robotics: Methods & Algorithms Today s Topic Nonlinear Least Squares Pose-Graph SLAM Incremental Smoothing and Mapping Feature-Based SLAM Filtering Problem: Motion Prediction

More information

Tightly-Integrated Visual and Inertial Navigation for Pinpoint Landing on Rugged Terrains

Tightly-Integrated Visual and Inertial Navigation for Pinpoint Landing on Rugged Terrains Tightly-Integrated Visual and Inertial Navigation for Pinpoint Landing on Rugged Terrains PhD student: Jeff DELAUNE ONERA Director: Guy LE BESNERAIS ONERA Advisors: Jean-Loup FARGES Clément BOURDARIAS

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

Optimizing Monocular Cues for Depth Estimation from Indoor Images

Optimizing Monocular Cues for Depth Estimation from Indoor Images Optimizing Monocular Cues for Depth Estimation from Indoor Images Aditya Venkatraman 1, Sheetal Mahadik 2 1, 2 Department of Electronics and Telecommunication, ST Francis Institute of Technology, Mumbai,

More information

Reconstructing Images of Bar Codes for Construction Site Object Recognition 1

Reconstructing Images of Bar Codes for Construction Site Object Recognition 1 Reconstructing Images of Bar Codes for Construction Site Object Recognition 1 by David E. Gilsinn 2, Geraldine S. Cheok 3, Dianne P. O Leary 4 ABSTRACT: This paper discusses a general approach to reconstructing

More information

Implementation of Odometry with EKF for Localization of Hector SLAM Method

Implementation of Odometry with EKF for Localization of Hector SLAM Method Implementation of Odometry with EKF for Localization of Hector SLAM Method Kao-Shing Hwang 1 Wei-Cheng Jiang 2 Zuo-Syuan Wang 3 Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung,

More information

A METHOD FOR EXTRACTING LINES AND THEIR UNCERTAINTY FROM ACOUSTIC UNDERWATER IMAGES FOR SLAM. David Ribas Pere Ridao José Neira Juan Domingo Tardós

A METHOD FOR EXTRACTING LINES AND THEIR UNCERTAINTY FROM ACOUSTIC UNDERWATER IMAGES FOR SLAM. David Ribas Pere Ridao José Neira Juan Domingo Tardós 6th IFAC Symposium on Intelligent Autonomous Vehicles IAV 2007, September 3-5 2007 Toulouse, France (To appear) A METHOD FOR EXTRACTING LINES AND THEIR UNCERTAINTY FROM ACOUSTIC UNDERWATER IMAGES FOR SLAM

More information

Localization, Where am I?

Localization, Where am I? 5.1 Localization, Where am I?? position Position Update (Estimation?) Encoder Prediction of Position (e.g. odometry) YES matched observations Map data base predicted position Matching Odometry, Dead Reckoning

More information

Simultaneous Localization

Simultaneous Localization Simultaneous Localization and Mapping (SLAM) RSS Technical Lecture 16 April 9, 2012 Prof. Teller Text: Siegwart and Nourbakhsh S. 5.8 Navigation Overview Where am I? Where am I going? Localization Assumed

More information

Motion Tracking and Event Understanding in Video Sequences

Motion Tracking and Event Understanding in Video Sequences Motion Tracking and Event Understanding in Video Sequences Isaac Cohen Elaine Kang, Jinman Kang Institute for Robotics and Intelligent Systems University of Southern California Los Angeles, CA Objectives!

More information

3D Modeling using multiple images Exam January 2008

3D Modeling using multiple images Exam January 2008 3D Modeling using multiple images Exam January 2008 All documents are allowed. Answers should be justified. The different sections below are independant. 1 3D Reconstruction A Robust Approche Consider

More information

Robotics. Lecture 8: Simultaneous Localisation and Mapping (SLAM)

Robotics. Lecture 8: Simultaneous Localisation and Mapping (SLAM) Robotics Lecture 8: Simultaneous Localisation and Mapping (SLAM) See course website http://www.doc.ic.ac.uk/~ajd/robotics/ for up to date information. Andrew Davison Department of Computing Imperial College

More information

Introduction to SLAM Part II. Paul Robertson

Introduction to SLAM Part II. Paul Robertson Introduction to SLAM Part II Paul Robertson Localization Review Tracking, Global Localization, Kidnapping Problem. Kalman Filter Quadratic Linear (unless EKF) SLAM Loop closing Scaling: Partition space

More information

BROWN UNIVERSITY Department of Computer Science Master's Project CS-95-M17

BROWN UNIVERSITY Department of Computer Science Master's Project CS-95-M17 BROWN UNIVERSITY Department of Computer Science Master's Project CS-95-M17 "Robotic Object Recognition: Utilizing Multiple Views to Recognize Partially Occluded Objects" by Neil A. Jacobson ,'. Robotic

More information

Lecture: Autonomous micro aerial vehicles

Lecture: Autonomous micro aerial vehicles Lecture: Autonomous micro aerial vehicles Friedrich Fraundorfer Remote Sensing Technology TU München 1/41 Autonomous operation@eth Zürich Start 2/41 Autonomous operation@eth Zürich 3/41 Outline MAV system

More information

CS4495/6495 Introduction to Computer Vision

CS4495/6495 Introduction to Computer Vision CS4495/6495 Introduction to Computer Vision 9C-L1 3D perception Some slides by Kelsey Hawkins Motivation Why do animals, people & robots need vision? To detect and recognize objects/landmarks Is that a

More information

DEALING WITH SENSOR ERRORS IN SCAN MATCHING FOR SIMULTANEOUS LOCALIZATION AND MAPPING

DEALING WITH SENSOR ERRORS IN SCAN MATCHING FOR SIMULTANEOUS LOCALIZATION AND MAPPING Inženýrská MECHANIKA, roč. 15, 2008, č. 5, s. 337 344 337 DEALING WITH SENSOR ERRORS IN SCAN MATCHING FOR SIMULTANEOUS LOCALIZATION AND MAPPING Jiří Krejsa, Stanislav Věchet* The paper presents Potential-Based

More information

Efficient SLAM Scheme Based ICP Matching Algorithm Using Image and Laser Scan Information

Efficient SLAM Scheme Based ICP Matching Algorithm Using Image and Laser Scan Information Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science (EECSS 2015) Barcelona, Spain July 13-14, 2015 Paper No. 335 Efficient SLAM Scheme Based ICP Matching Algorithm

More information

Transactions on Information and Communications Technologies vol 16, 1996 WIT Press, ISSN

Transactions on Information and Communications Technologies vol 16, 1996 WIT Press,   ISSN ransactions on Information and Communications echnologies vol 6, 996 WI Press, www.witpress.com, ISSN 743-357 Obstacle detection using stereo without correspondence L. X. Zhou & W. K. Gu Institute of Information

More information

BBR Progress Report 006: Autonomous 2-D Mapping of a Building Floor

BBR Progress Report 006: Autonomous 2-D Mapping of a Building Floor BBR Progress Report 006: Autonomous 2-D Mapping of a Building Floor Andy Sayler & Constantin Berzan November 30, 2010 Abstract In the past two weeks, we implemented and tested landmark extraction based

More information

Position-Based Navigation Using Multiple Homographies

Position-Based Navigation Using Multiple Homographies Position-Based Navigation Using Multiple Homographies Eduardo Montijano DIIS - IA University of Zaragoza, Spain emonti@unizar.es Carlos Sagues DIIS - IA University of Zaragoza, Spain csagues@unizar.es

More information

Zürich. Roland Siegwart Margarita Chli Martin Rufli Davide Scaramuzza. ETH Master Course: L Autonomous Mobile Robots Summary

Zürich. Roland Siegwart Margarita Chli Martin Rufli Davide Scaramuzza. ETH Master Course: L Autonomous Mobile Robots Summary Roland Siegwart Margarita Chli Martin Rufli Davide Scaramuzza ETH Master Course: 151-0854-00L Autonomous Mobile Robots Summary 2 Lecture Overview Mobile Robot Control Scheme knowledge, data base mission

More information

SLAM with SIFT (aka Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks ) Se, Lowe, and Little

SLAM with SIFT (aka Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks ) Se, Lowe, and Little SLAM with SIFT (aka Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks ) Se, Lowe, and Little + Presented by Matt Loper CS296-3: Robot Learning and Autonomy Brown

More information

Simultaneous Localization and Mapping with Monocamera: Detection of Landing Zones

Simultaneous Localization and Mapping with Monocamera: Detection of Landing Zones 1 Simultaneous Localization and Mapping with Monocamera: Detection of Landing Zones Nuno M. B. Moutinho ISR - Instituto de Sistemas e Robótica; Departamento de Engenharia Aerospacial; IST - Instituto Superior

More information

Robot localization method based on visual features and their geometric relationship

Robot localization method based on visual features and their geometric relationship , pp.46-50 http://dx.doi.org/10.14257/astl.2015.85.11 Robot localization method based on visual features and their geometric relationship Sangyun Lee 1, Changkyung Eem 2, and Hyunki Hong 3 1 Department

More information

Motion. 1 Introduction. 2 Optical Flow. Sohaib A Khan. 2.1 Brightness Constancy Equation

Motion. 1 Introduction. 2 Optical Flow. Sohaib A Khan. 2.1 Brightness Constancy Equation Motion Sohaib A Khan 1 Introduction So far, we have dealing with single images of a static scene taken by a fixed camera. Here we will deal with sequence of images taken at different time intervals. Motion

More information

15 Years of Visual SLAM

15 Years of Visual SLAM 15 Years of Visual SLAM Andrew Davison Robot Vision Group and Dyson Robotics Laboratory Department of Computing Imperial College London www.google.com/+andrewdavison December 18, 2015 What Has Defined

More information

Live Metric 3D Reconstruction on Mobile Phones ICCV 2013

Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 Main Contents 1. Target & Related Work 2. Main Features of This System 3. System Overview & Workflow 4. Detail of This System 5. Experiments 6.

More information

Jo-Car2 Autonomous Mode. Path Planning (Cost Matrix Algorithm)

Jo-Car2 Autonomous Mode. Path Planning (Cost Matrix Algorithm) Chapter 8.2 Jo-Car2 Autonomous Mode Path Planning (Cost Matrix Algorithm) Introduction: In order to achieve its mission and reach the GPS goal safely; without crashing into obstacles or leaving the lane,

More information

High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images

High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images MECATRONICS - REM 2016 June 15-17, 2016 High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images Shinta Nozaki and Masashi Kimura School of Science and Engineering

More information

On the Use of Inverse Scaling in Monocular SLAM

On the Use of Inverse Scaling in Monocular SLAM 29 IEEE International Conference on Robotics and Automation Kobe International Conference Center Kobe, Japan, May 12-17, 29 On the Use of Inverse Scaling in Monocular SLAM Daniele Marzorati, Matteo Matteucci,

More information

An Extended Line Tracking Algorithm

An Extended Line Tracking Algorithm An Extended Line Tracking Algorithm Leonardo Romero Muñoz Facultad de Ingeniería Eléctrica UMSNH Morelia, Mich., Mexico Email: lromero@umich.mx Moises García Villanueva Facultad de Ingeniería Eléctrica

More information

Sensor Modalities. Sensor modality: Different modalities:

Sensor Modalities. Sensor modality: Different modalities: Sensor Modalities Sensor modality: Sensors which measure same form of energy and process it in similar ways Modality refers to the raw input used by the sensors Different modalities: Sound Pressure Temperature

More information

Robot Localisation and Mapping with Stereo Vision

Robot Localisation and Mapping with Stereo Vision Robot Localisation and Mapping with Stereo Vision A. CUMANI, S. DENASI, A. GUIDUCCI, G. QUAGLIA Istituto Elettrotecnico Nazionale Galileo Ferraris str. delle Cacce, 91 - I-10135 Torino ITALY Abstract:

More information

Homography Based Kalman Filter for Mosaic Building. Applications to UAV position estimation

Homography Based Kalman Filter for Mosaic Building. Applications to UAV position estimation 2007 IEEE International Conference on Robotics and Automation Roma, Italy, 10-14 April 2007 ThA12.1 Homography Based Kalman Filter for Mosaic Building. Applications to UAV position estimation Fernando

More information

Camera Model and Calibration

Camera Model and Calibration Camera Model and Calibration Lecture-10 Camera Calibration Determine extrinsic and intrinsic parameters of camera Extrinsic 3D location and orientation of camera Intrinsic Focal length The size of the

More information

ME 597/747 Autonomous Mobile Robots. Mid Term Exam. Duration: 2 hour Total Marks: 100

ME 597/747 Autonomous Mobile Robots. Mid Term Exam. Duration: 2 hour Total Marks: 100 ME 597/747 Autonomous Mobile Robots Mid Term Exam Duration: 2 hour Total Marks: 100 Instructions: Read the exam carefully before starting. Equations are at the back, but they are NOT necessarily valid

More information

ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall Midterm Examination

ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall Midterm Examination ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall 2008 October 29, 2008 Notes: Midterm Examination This is a closed book and closed notes examination. Please be precise and to the point.

More information

Estimation of Camera Motion with Feature Flow Model for 3D Environment Modeling by Using Omni-Directional Camera

Estimation of Camera Motion with Feature Flow Model for 3D Environment Modeling by Using Omni-Directional Camera Estimation of Camera Motion with Feature Flow Model for 3D Environment Modeling by Using Omni-Directional Camera Ryosuke Kawanishi, Atsushi Yamashita and Toru Kaneko Abstract Map information is important

More information

Lecture 19: Depth Cameras. Visual Computing Systems CMU , Fall 2013

Lecture 19: Depth Cameras. Visual Computing Systems CMU , Fall 2013 Lecture 19: Depth Cameras Visual Computing Systems Continuing theme: computational photography Cameras capture light, then extensive processing produces the desired image Today: - Capturing scene depth

More information

D-SLAM: Decoupled Localization and Mapping for Autonomous Robots

D-SLAM: Decoupled Localization and Mapping for Autonomous Robots D-SLAM: Decoupled Localization and Mapping for Autonomous Robots Zhan Wang, Shoudong Huang, and Gamini Dissanayake ARC Centre of Excellence for Autonomous Systems (CAS), Faculty of Engineering, University

More information

Uncertainties: Representation and Propagation & Line Extraction from Range data

Uncertainties: Representation and Propagation & Line Extraction from Range data 41 Uncertainties: Representation and Propagation & Line Extraction from Range data 42 Uncertainty Representation Section 4.1.3 of the book Sensing in the real world is always uncertain How can uncertainty

More information

Marcel Worring Intelligent Sensory Information Systems

Marcel Worring Intelligent Sensory Information Systems Marcel Worring worring@science.uva.nl Intelligent Sensory Information Systems University of Amsterdam Information and Communication Technology archives of documentaries, film, or training material, video

More information

Introduction to Mobile Robotics. SLAM: Simultaneous Localization and Mapping

Introduction to Mobile Robotics. SLAM: Simultaneous Localization and Mapping Introduction to Mobile Robotics SLAM: Simultaneous Localization and Mapping The SLAM Problem SLAM is the process by which a robot builds a map of the environment and, at the same time, uses this map to

More information

CS 4758: Automated Semantic Mapping of Environment

CS 4758: Automated Semantic Mapping of Environment CS 4758: Automated Semantic Mapping of Environment Dongsu Lee, ECE, M.Eng., dl624@cornell.edu Aperahama Parangi, CS, 2013, alp75@cornell.edu Abstract The purpose of this project is to program an Erratic

More information