Localization Assistance for Multiple Mobile Robots using Target Tracking Techniques

Size: px
Start display at page:

Download "Localization Assistance for Multiple Mobile Robots using Target Tracking Techniques"

Transcription

1 Localization Assistance for Multiple Mobile Robots using Target Tracing Techniques Peshala Jayaseara a, Hidei Hashimoto b and Taashi Kubota c a Dept. of Electrical Engineering, University of Toyo, Toyo, Japan b Dept. of Electrical, Electronics and Communication Engineering, Chuo University, Toyo, Japan c Inst. of Space and Astronautical Science (ISAS), JAXA, Japan peshala@nnl.isas.jaxa.jp Abstract Developing autonomous mobile robots that can coexist with human in populated environments is still considered a big challenge. To address this problem the authors propose a novel scheme to assist mobile robots by providing localization information externally. In the proposed scheme, the environment is sensed using a laser range finder and camera based sensor unit. Using Rao- Blacwellized particle filter technique, the robots that need assistance are continuously traced. In contrast with conventional laser range finder based tracing systems, the placement of sensor is changed to a level above average human height and the mobile robots are modified by attaching a cylindrical pole. The experiments show the validity of the proposed scheme for simultaneous localization assistance for multiple mobile robots. Two mobile robots were simultaneously navigated in given trajectories using assistance data, successfully. Keywords Localization, Mobile Robots, Target Tracing, Particle Filter I. INTRODUCTION Daily human environments are dynamic, unpredictable and populated. These real environments pose many challenges for conventional self-contained autonomous mobile robots even if they are equipped with as many sensors as possible. Adaptability to real environments comes at a cost of the mobile robot s computational capability, which, due to its size and mobility, is limited. Thus, considering the state-of-art technologies, it is difficult to expect a capable mobile robot navigating all by itself in complex human environments even in near future. Humans tend to depend on some assistance to minimize both the effort and time put into navigation. This human behavior can be imitated in the field of autonomous navigation for mobile robots. This idea motivates the need for a proper assistance scheme for autonomous navigation and such an assistance system can act as the missing building bloc to provide fully autonomous capabilities for navigation in human environments. More specifically, the project objective is to develop a structured assistance system for mobile robots navigating in crowded human environments. The case where such a localization assistance system would not have any prior nowledge about the mobile robots (e.g. shape, features) is considered. Furthermore, the authors intend to reduce the on-board sensors, eliminate the need for any other tags and consider minimum environment modification. The mobile robots will therefore not be equipped with any tags, heading reference systems and rely on information it obtains from the assistance system. In order to realize a structured mobile robot assistance scheme, two important aspects should be considered; the nature of assistance and a suitable methodology to implement it. In this research, the authors have narrowed the scope of the assistance system to provision of only localization information. Conventional laser range finder (LRF) based scan matching and camera based localization techniques can easily fail in complex human environments due to inability to see landmars (occlusion), or complexity of the environment. Other localization systems [][2] needs the environment to be modified severely and to undergo time consuming calibration procedures. To implement the proposed assistance system, target tracing techniques have been utilized. There has been considerable research done on tracing moving targets [3]-[6]. However, in these wors, traced information is often used from the viewpoint of the tracer and seldom used for the benefit of the targets being traced. As described in [7] target tracing can be effectively used to extract localization of mobile robots and assist multiple mobile robots in autonomous navigation; the authors have named the system as intelligent assistance (IA). In this paper the authors present their latest results of the intelligent assistance system. II. RELATED WORK ispace, proposed by Hashimoto laboratory [8], is an ambient intelligent space with ubiquitous distributed sensory intelligence and actuators for manipulating the space. Robot localization using on-board and distributed sensors has been proposed for ispace in [9]. The proposed system follows the same idea of [9] and has been improvised. Autonomous City Explorer Project [0] attempts to address the problem of autonomous mobile

2 robot navigation in natural, populated environments with external human assistance. The ambiguity in extracted visual information can lead to inconsistencies in information perception. As the third option, mobile robots can see help from other robots in the environment using cooperative localization (CL) technique. Ref.[]-[3] provide some of the example implementations of CL. In all these approaches each mobile robot shares its belief with the other members of the group. Amount of transmitted information and computational complexity are the two major issues that cannot be overlooed for a mobile robot which has limited resources. Moreover, if the mobile robots do not have a protocol for communication with each other, then CL cannot be established to increase individual localization accuracy. III. SYSTEM ARCHITECTURE The schematic diagram of the proposed system is given in Fig.. neighbor classifier. LRF cluster means are then adjusted to estimate the center position of the mobile robot. B. Camera based Target Tracing Initialization The assistant system has no prior nowledge of the robots to be served. Therefore, there should be a mechanism to initialize the tracing of each mobile robot. It can be expected that the mobile robots be occluded in the populated environment and the assistant has to automatically find some clue to detect it. The proposed scheme for initial attachment is by using a blining signal light (red bulb), with a nown frequency of blining, attached to the cylindrical pole of the mobile robot. At initialization the mobile robot stays stationary and the blining frequency is agreed upon by both parties at the time of initialization. An AND operation is performed between the thresholded image of the current frame and the thresholded image of the (r/f) th frame before the current frame; the blining frequency f and the frame rate r of the camera are nown, and f is chosen such that (r/f) is an integer. If the current frame contains the lit signal light, then an AND operation is performed with a frame that also contained another lit signal light. This can isolate the position of the signal light as explained in Fig. 2. The angle of the signal light is computed and it is matched with the nearest angle of LRF cluster means. The selected LRF measurement is used as the initial estimate for initializing tracing for the particular mobile robot. This is illustrated in Fig. 3. Fig.. Schematic diagram of the proposed system. A SICK LMS 29 LRF and a Point Grey Dragonfly2 IEEE firewire camera based sensor unit is used to detect mobile robots. The need for fusion of camera with LRF arises because the differentiation between different targets using only LRF data cannot be done. In the initialization phase, the robot is detected by the tracing initializer of the IA vision subsystem and by LRF, simultaneously. After correctly associating camera observations with corresponding LRF observations, this fused information is used for tracing mobile robots by a particle filter based tracer. Output from the particle filter tracer will be fed-bac to mobile robots as assistance information. A. LRF Data Processing In LRF data, a bacground subtraction method is utilized, and mobile robots are detected as foreground objects. The LRF scan plane is changed (section IV), and at this scan level the bacground hardly changes. Thus, bacground subtraction method for detection is robust. The laser scan points are clustered using a nearest Fig. 2. Capturing the light source based on difference images and the blining frequency. Fig. 3. Detection of the angle of the blining light source of a mobile robot and the selection of the associated LRF measurement

3 Fig. 4. Illustration of LRF placement and robot modification In doing so, not only its position but its heading direction can be estimated. This is because, most robots are non-holonomic, using differential-drive systems or Acerman steered systems and for such robots, the nonholonomic constraints limit the robot s velocity in each configuration (x, y, θ). As a result, if the interval between two successive measurements is small, its heading angle can be computed using: y& θ = tan x& (2) except x& < threshold _ x& AND y& < threshold _ y& This is illustrated in Fig. 5. It is made sure θ is not calculated when the robot is stationary or rotating with small translational velocities, which in turn results in noisy θ calculations (discontinuity in θ calculation). IV. MOBILE ROBOT MODIFICATION Different mobile robots have different base shapes. And, the LRF cluster center varies depending on the mobile robot s base shape as well as its heading angle. To be able to detect mobile robots in crowded environments and to trac the same position of robots at all times the robot platform is modified by attaching a vertical cylindrical pole with its height greater than average human height. The LRF placement is also changed to an overhead level at 2m from ground. This is illustrated in Fig. 4. V. MULTIPLE TARGET TRACKING IN CLUTTER The problem of data association maes multiple target tracing (MTT) a much harder tas than single target tracing. In MTT, the algorithm has to estimate which targets produced the measurements, before it is able to use them in actual tracing. The Rao-Blacwellized Monte Carlo data association algorithm proposed by S ar a et al.[4] estimates data associations with a sequential importance resampling (SIR) particle filter and the other parts with a Kalman filter. This idea can be directly used in the MTT in clutter case. Due to the conditional independences between the targets, the full Kalman filter prediction and update steps for all targets can be reduced to independent single target predictions and updates. Because the targets are a priori independent, conditional on the data associations C, the targets will remain independent during tracing. A. State Space Model Target state should be chosen in such a way that localization information of a target could be obtained from its state. Target state X is represented using its (x,y) position and velocities ( x, y) in the two dimensional Cartesian coordinates: X = x y x& y& () [ ] T Fig. 5. Illustration of the validity of heading angle estimation approach A discretized Wiener process velocity model is used as the dynamic model of a target described as follows: X = A X + w + cv 0 T 0 (3) 0 0 T A = cv where A cv is the state-transition matrix, T is the sampling interval and w is process noise. The nonlinear measurement model is a range-bearing (r, θ) model of the form: Z = f ( X ) + v 2 2 x + y (4) r = y + v θ tan x where Z is measurement and v is measurement noise. B. Algorithm Implementation In accordance with the method proposed by Särä in [4], the final Rao-Blacwellized particle filter implementation is as follows: Perform KF predictions for the means m (i) - and the covariances P (i) - of particles i =,,N. m = A m (5) T P = A P A + Q

4 Using SIR particle filter draw new data association C for each particle in i =,,N from importance distribution π C Z, C p C Z C (6) ( ) ( ) : : = :, : Using Bayes rule, p ( C Z:, C : ) (7) p( Z C, Z:, C : ) p( C C : ) Therefore, instead of from (6), we can draw a new association from (7). Calculate new unnormalized weights as follows: * * p( Z Z:, C : ) p( C C : ) w = w (8) π( C Z:, C : ) Normalize the weights Perform the KF updates for each of the particles conditional on the drawn data association variable V = Z h( m ) S K m h = x = P = m m h x + K h x m T m [ S ] T [ K ] T P = P K S If the effective number of particles neff = N (0) 2 ( w ) P i= V + R is too low, perform resampling. After the set of particles have been acquired, the filtering distribution can be approximated as N p( X, λ Z ) w δ ( λ λ ) N( X m, P () : ) i= VI. ROBOT-SIDE IMPLEMENTATION Robot-side implementation to mae use of IA information is described, here. A. EKF based Sensor Fusion An EKF based sensor fusion mechanism is implemented at the robot-side to obtain its pose by fusing IA data with odometry measurements; no attitude, heading reference sensors are used. The need for data fusion arises because of the fact that heading angle estimation undergoes discontinuities in IA as explained in section V.A. System Model: a nonlinear system model for the state transition in the form: x = g( x, v, w ) + ε x x + v T cos( θ ) (2) y = y + v T θ sin( ) + ε θ θ + w T x represents the state vector, v, w represents control inputs and ε is a Gaussian random vector (9) that models uncertainty introduced by the state transition. Measurement Model: a linear measurement model in the form: z = Hx + δ 0 0 (3) H = Both assistance and odometry measurements are similar in structure to the state vector, and therefore, the same measurement model can be used to update the filter. Sensor fusion taes place at the Kalman update step, where the filter is updated sequentially using all the sensor measurements (Odometry and IA data) for that particular instance. However, the mismatch of timestamps of the two measurements prevents us from applying such an update straightaway. This is overcome by interpolating one measurement to the other measurements timestamp. As odometry data can drift arbitrary over time, the raw odometry cannot be used as it is in the EKF. The interpretation of odometry data is changed continuously so that the odometry error accumulated up to a given point of time is eliminated. The interpretation is changed based on the pose estimation output of the EKF. VII. EXPERIMENTS AND RESULTS A. Simulations of Multiple Target Tracing in the presence of Clutter Tracing of three targets in the presence of clutter is simulated using MATLAB software. The results are given in Fig. 6. It is observed that the results of the Rao- Blacwellized particle filter tracer show a very good accuracy compared to the real trajectories for all the three targets even in the presence of clutter (Fig. 6 (a)). For all three targets, the mean position estimation error is 2.5cm and the mean heading angle estimation error is 2 degrees. As the heading angle of a target cannot be directly obtained from LRF readings, it is important to examine the accuracy of the proposed method for heading angle estimation. The three targets were given a continuous change of heading angle maing them to move in curved trajectories. Fig. 6 (b), (c) and (d) compare the heading angles of target, target2 and target3 respectively to their estimated heading angles. In the simulations, it can be observed that the estimated values follow the real values and the obtained error is within acceptable ranges for a mobile robot. In each graph in Fig. 6 (b), (c) and (d) there is an initial overshoot in the estimated angle. This should not come at a surprise as this region is where the heading angle is not calculated as the velocity state variables are smaller than their thresholds as explained before in section V.A.

5 Fig. 6. Simulation Results (a) Position comparison (b) Heading angle comparison for target (c) Heading angle comparison for target2 (d) Heading angle comparison for target3 B. Assisted Navigation Experiments In the experimental setting, as shown in Fig. 7, the mobile robot(s) is given four sub-goals (in a rectangle) to navigate using IAs assistance. The mobile robot does not contain any sensors apart from its built-in odometry. Assisted navigation experiments are conducted for both single and dual robots and their raw odometry versus the EKF pose output is examined to identify how well the assistance information has helped the robots to minimize the localization error and how well it can navigate on a given trajectory using IA support. The zone positioning system (ZPS) system of Hashimoto laboratory is used to compare the estimations with the actual localization. The results are given in Fig. 8 and Fig. 9 for dual robot experiment. The reason for choosing such a rectangular path was to examine the behavior of robot pose estimation when the heading angle provided by the intelligent assistant is invalid; at sharp corners in the trajectory the robots will be maing pure rotations without any translation velocity and only the position information from IA will be valid. Nevertheless, it is evident from the two figures that the pose estimation is not severely affected because of the EKF based sensor fusion implementation at robot-side. It can be clearly observed that, even after one cycle of navigation via the four given sub-goals, the raw odometry had considerably deviated from its actual localization. However, by fusing intelligent assistance data with odometry and changing the odometry interpretation the mobile robots have managed to fulfill the navigation tas successfully. Fig. 7. Assisted navigation - snapshots of (a) single mobile robot (b) multiple mobile robots experiment Fig. 8. Comparison between real odometry data, robot EKF output and ZPS output for robot#

6 REFERENCES Fig. 9. Comparison between real odometry data, robot EKF output and ZPS output for robot#2 VIII. CONCLUSION By imitating how humans navigate in complex environments with the help of assistance from others, the same behavior was mimiced for mobile robots by introducing and developing a structured assistance scheme, named intelligent assistance. Mobile robots are detected using a laser range finder and a camera based sensor unit and traced by employing the particle filter technique. The experiment results show the validity and the applicability of IA for multiple robot assistance, with an IA throughput: 0Hz, position estimation error: 5.5cm and heading angle error: By incorporating localization assistance information with rather noisy odometry measurements and a proper implementation at robot-side, the self-localization uncertainty of mobile robots is reduced and thereby the robots could be navigated in expected trajectories, even without any heading reference system, with a minimized error. A. Future Directions In the proposed scheme, the heading angle estimation undergoes discontinuities. Incorporating camera images to determine the heading angle in such situations is a potential solution to this problem. In the current implementation, the sensor unit static is ept stationary. However, if the sensor unit is mobile, better detection as well as increased coverage is possible by optimal positioning of the sensor unit. The authors are currently investigating the possibilities of transforming the intelligent assistant into a mobile intelligent assistant (MIA) using a mobile platform. [] Nissana Bodhi Priyantha, The cricet indoor location system, PhD Thesis, Massachusetts Institute of Technology, [2] R. Orr and G. Abowd, The Smart Floor: A mechanism for natural user identification and tracing, in Proceedings of the Conference on Human Factors in Computing Systems (CHI 00), pp , [3] D. Brscic and H. Hashimoto, Tracing of humans inside intelligent space using static and mobile sensors, in 33rd Annual Conference of the IEEE Industrial Electronics Society IECON, pp. 0-5, [4] S. S ar a, A. Vehtari, and J. Lampinen, Rao- Blacwellized particle filter for multiple target tracing, Information Fusion Journal, vol. 8, no., pp. 2-5, [5] R. Kurazume, H. Yamada, K. Muraami, Y. Iwashita, and T. Hasegawa, Target tracing using SIR and MCMC particle filters by multiple cameras and laser range finders, in International Conference on Intelligent Robots and Systems, IROS, pp , [6] K. Naamura et al., Tracing pedestrians using multiple single-row laser range scanners and its reliability evaluation, Systems and computers in Japan, vol. 37, no. 7, pp. -, [7] P. G. Jayaseara, Y. E. Song, T. Sasai, and H. Hashimoto, Intelligent assistance in localization for mobile robots, in The 8th France-Japan and 6th Europe- Asia Congress on Mechatronics, pp , Yoohama, Japan, November 22-24, 200. [8] J. H. Lee and H. Hashimoto, Intelligent space - concept and contents, Advanced Robotics, vol. 6, no. 3, pp , [9] D. Brscic and H. Hashimoto, Model based robot localization using onboard and distributed laser range finders, in IEEE/RSJ International Conference on Intelligent Robots and Systems, pp , [0] G. Lidoris, F. Rohrmuller, D.Wollherr, and M. Buss, The autonomous city explorer (ACE) project-mobile robot navigation in highly populated urban environments, in IEEE International Conference on Robotics and Automation ICRA 09, pp , [] D. Fox, W. Burgard, H. Kruppa, and S. Thrun, A probabilistic approach to collaborative multi-robot localization, in Autonomous Robots: Special Issue on Heterogeneous Multi-Robot Systems, vol. 8, no. 3, pp , [2] A. Howard, M.J. Mataric, and G.S. Suhatme, Localization for mobile robot teams using maximum lielihood estimation, in International Conference on Intelligent Robot and Systems (IROS02), vol. 3, pp , [3] A. Howard, Multi-robot simultaneous localization and mapping using particle filters, in Proc. Robot. Sci. Syst., Cambridge, [4] S. S ar a, A. Vehtari, J. Lampinen, Rao-Blacwellized Monte Carlo data association for multiple target tracing, in Proceedings of the Seventh International Conference on Information Fusion, vol. I, pp , 2004.

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

Matching Evaluation of 2D Laser Scan Points using Observed Probability in Unstable Measurement Environment

Matching Evaluation of 2D Laser Scan Points using Observed Probability in Unstable Measurement Environment Matching Evaluation of D Laser Scan Points using Observed Probability in Unstable Measurement Environment Taichi Yamada, and Akihisa Ohya Abstract In the real environment such as urban areas sidewalk,

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

Where s the Boss? : Monte Carlo Localization for an Autonomous Ground Vehicle using an Aerial Lidar Map

Where s the Boss? : Monte Carlo Localization for an Autonomous Ground Vehicle using an Aerial Lidar Map Where s the Boss? : Monte Carlo Localization for an Autonomous Ground Vehicle using an Aerial Lidar Map Sebastian Scherer, Young-Woo Seo, and Prasanna Velagapudi October 16, 2007 Robotics Institute Carnegie

More information

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Evaluation

More information

Localization of Multiple Robots with Simple Sensors

Localization of Multiple Robots with Simple Sensors Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls, Canada July 2005 Localization of Multiple Robots with Simple Sensors Mike Peasgood and Christopher Clark Lab

More information

Humanoid Robotics. Monte Carlo Localization. Maren Bennewitz

Humanoid Robotics. Monte Carlo Localization. Maren Bennewitz Humanoid Robotics Monte Carlo Localization Maren Bennewitz 1 Basis Probability Rules (1) If x and y are independent: Bayes rule: Often written as: The denominator is a normalizing constant that ensures

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

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

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

Kalman Filter Based. Localization

Kalman Filter Based. Localization Autonomous Mobile Robots Localization "Position" Global Map Cognition Environment Model Local Map Path Perception Real World Environment Motion Control Kalman Filter Based Localization & SLAM Zürich Autonomous

More information

3D Terrain Sensing System using Laser Range Finder with Arm-Type Movable Unit

3D Terrain Sensing System using Laser Range Finder with Arm-Type Movable Unit 3D Terrain Sensing System using Laser Range Finder with Arm-Type Movable Unit 9 Toyomi Fujita and Yuya Kondo Tohoku Institute of Technology Japan 1. Introduction A 3D configuration and terrain sensing

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

USING 3D DATA FOR MONTE CARLO LOCALIZATION IN COMPLEX INDOOR ENVIRONMENTS. Oliver Wulf, Bernardo Wagner

USING 3D DATA FOR MONTE CARLO LOCALIZATION IN COMPLEX INDOOR ENVIRONMENTS. Oliver Wulf, Bernardo Wagner USING 3D DATA FOR MONTE CARLO LOCALIZATION IN COMPLEX INDOOR ENVIRONMENTS Oliver Wulf, Bernardo Wagner Institute for Systems Engineering (RTS/ISE), University of Hannover, Germany Mohamed Khalaf-Allah

More information

Practical Course WS12/13 Introduction to Monte Carlo Localization

Practical Course WS12/13 Introduction to Monte Carlo Localization Practical Course WS12/13 Introduction to Monte Carlo Localization Cyrill Stachniss and Luciano Spinello 1 State Estimation Estimate the state of a system given observations and controls Goal: 2 Bayes Filter

More information

Optical Flow-Based Person Tracking by Multiple Cameras

Optical Flow-Based Person Tracking by Multiple Cameras Proc. IEEE Int. Conf. on Multisensor Fusion and Integration in Intelligent Systems, Baden-Baden, Germany, Aug. 2001. Optical Flow-Based Person Tracking by Multiple Cameras Hideki Tsutsui, Jun Miura, and

More information

Probabilistic Robotics

Probabilistic Robotics Probabilistic Robotics FastSLAM Sebastian Thrun (abridged and adapted by Rodrigo Ventura in Oct-2008) The SLAM Problem SLAM stands for simultaneous localization and mapping The task of building a map while

More information

Pedestrian Detection Using Multi-layer LIDAR

Pedestrian Detection Using Multi-layer LIDAR 1 st International Conference on Transportation Infrastructure and Materials (ICTIM 2016) ISBN: 978-1-60595-367-0 Pedestrian Detection Using Multi-layer LIDAR Mingfang Zhang 1, Yuping Lu 2 and Tong Liu

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

DYNAMIC TRIANGULATION FOR MOBILE ROBOT LOCALIZATION USING AN ANGULAR STATE KALMAN FILTER. Josep Maria Font, Joaquim A. Batlle

DYNAMIC TRIANGULATION FOR MOBILE ROBOT LOCALIZATION USING AN ANGULAR STATE KALMAN FILTER. Josep Maria Font, Joaquim A. Batlle DYNAMIC TRIANGULATION FOR MOBILE ROBOT LOCALIZATION USING AN ANGULAR STATE KALMAN FILTER Josep Maria Font, Joaquim A. Batlle Department of Mechanical Engineering Technical University of Catalonia (UPC)

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

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

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

CAMERA POSE ESTIMATION OF RGB-D SENSORS USING PARTICLE FILTERING

CAMERA POSE ESTIMATION OF RGB-D SENSORS USING PARTICLE FILTERING CAMERA POSE ESTIMATION OF RGB-D SENSORS USING PARTICLE FILTERING By Michael Lowney Senior Thesis in Electrical Engineering University of Illinois at Urbana-Champaign Advisor: Professor Minh Do May 2015

More information

IROS 05 Tutorial. MCL: Global Localization (Sonar) Monte-Carlo Localization. Particle Filters. Rao-Blackwellized Particle Filters and Loop Closing

IROS 05 Tutorial. MCL: Global Localization (Sonar) Monte-Carlo Localization. Particle Filters. Rao-Blackwellized Particle Filters and Loop Closing IROS 05 Tutorial SLAM - Getting it Working in Real World Applications Rao-Blackwellized Particle Filters and Loop Closing Cyrill Stachniss and Wolfram Burgard University of Freiburg, Dept. of Computer

More information

Radar Detection Improvement by Integration of Multi- Object Tracking

Radar Detection Improvement by Integration of Multi- Object Tracking Radar Detection Improvement by Integration of Multi- Object Tracing Lingmin Meng Research and Technology Center Robert Bosch Corp. Pittsburgh, PA, U.S.A. lingmin.meng@rtc.bosch.com Wolfgang Grimm Research

More information

Overview. EECS 124, UC Berkeley, Spring 2008 Lecture 23: Localization and Mapping. Statistical Models

Overview. EECS 124, UC Berkeley, Spring 2008 Lecture 23: Localization and Mapping. Statistical Models Introduction ti to Embedded dsystems EECS 124, UC Berkeley, Spring 2008 Lecture 23: Localization and Mapping Gabe Hoffmann Ph.D. Candidate, Aero/Astro Engineering Stanford University Statistical Models

More information

Robot Mapping. A Short Introduction to the Bayes Filter and Related Models. Gian Diego Tipaldi, Wolfram Burgard

Robot Mapping. A Short Introduction to the Bayes Filter and Related Models. Gian Diego Tipaldi, Wolfram Burgard Robot Mapping A Short Introduction to the Bayes Filter and Related Models Gian Diego Tipaldi, Wolfram Burgard 1 State Estimation Estimate the state of a system given observations and controls Goal: 2 Recursive

More information

Probabilistic Robotics. FastSLAM

Probabilistic Robotics. FastSLAM Probabilistic Robotics FastSLAM The SLAM Problem SLAM stands for simultaneous localization and mapping The task of building a map while estimating the pose of the robot relative to this map Why is SLAM

More information

Adapting the Sample Size in Particle Filters Through KLD-Sampling

Adapting the Sample Size in Particle Filters Through KLD-Sampling Adapting the Sample Size in Particle Filters Through KLD-Sampling Dieter Fox Department of Computer Science & Engineering University of Washington Seattle, WA 98195 Email: fox@cs.washington.edu Abstract

More information

Real-time target tracking using a Pan and Tilt platform

Real-time target tracking using a Pan and Tilt platform Real-time target tracking using a Pan and Tilt platform Moulay A. Akhloufi Abstract In recent years, we see an increase of interest for efficient tracking systems in surveillance applications. Many of

More information

Interacting Object Tracking in Crowded Urban Areas

Interacting Object Tracking in Crowded Urban Areas Interacting Object Tracing in Crowded Urban Areas Chieh-Chih Wang, Tzu-Chien Lo and Shao-Wen Yang Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan Email:

More information

Localization algorithm using a virtual label for a mobile robot in indoor and outdoor environments

Localization algorithm using a virtual label for a mobile robot in indoor and outdoor environments Artif Life Robotics (2011) 16:361 365 ISAROB 2011 DOI 10.1007/s10015-011-0951-7 ORIGINAL ARTICLE Ki Ho Yu Min Cheol Lee Jung Hun Heo Youn Geun Moon Localization algorithm using a virtual label for a mobile

More information

Scale-invariant visual tracking by particle filtering

Scale-invariant visual tracking by particle filtering Scale-invariant visual tracing by particle filtering Arie Nahmani* a, Allen Tannenbaum a,b a Dept. of Electrical Engineering, Technion - Israel Institute of Technology, Haifa 32000, Israel b Schools of

More information

An Overview of a Probabilistic Tracker for Multiple Cooperative Tracking Agents

An Overview of a Probabilistic Tracker for Multiple Cooperative Tracking Agents An Overview of a Probabilistic Tracker for Multiple Cooperative Tracking Agents Roozbeh Mottaghi and Shahram Payandeh School of Engineering Science Faculty of Applied Sciences Simon Fraser University Burnaby,

More information

Precise indoor localization of multiple mobile robots with adaptive sensor fusion using odometry and vision data

Precise indoor localization of multiple mobile robots with adaptive sensor fusion using odometry and vision data Preprints of the 9th World Congress The International Federation of Automatic Control Cape Town, South Africa. August 4-9, 04 Precise indoor localization of multiple mobile robots with adaptive sensor

More information

Extended target tracking using PHD filters

Extended target tracking using PHD filters Ulm University 2014 01 29 1(35) With applications to video data and laser range data Division of Automatic Control Department of Electrical Engineering Linöping university Linöping, Sweden Presentation

More information

Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments

Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments Proc. 2001 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems pp. 31-36, Maui, Hawaii, Oct./Nov. 2001. Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments Hiroshi

More information

Tracking Multiple Moving Objects with a Mobile Robot

Tracking Multiple Moving Objects with a Mobile Robot Tracking Multiple Moving Objects with a Mobile Robot Dirk Schulz 1 Wolfram Burgard 2 Dieter Fox 3 Armin B. Cremers 1 1 University of Bonn, Computer Science Department, Germany 2 University of Freiburg,

More information

Online Simultaneous Localization and Mapping in Dynamic Environments

Online Simultaneous Localization and Mapping in Dynamic Environments To appear in Proceedings of the Intl. Conf. on Robotics and Automation ICRA New Orleans, Louisiana, Apr, 2004 Online Simultaneous Localization and Mapping in Dynamic Environments Denis Wolf and Gaurav

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

EKF Localization and EKF SLAM incorporating prior information

EKF Localization and EKF SLAM incorporating prior information EKF Localization and EKF SLAM incorporating prior information Final Report ME- Samuel Castaneda ID: 113155 1. Abstract In the context of mobile robotics, before any motion planning or navigation algorithm

More information

Laserscanner Based Cooperative Pre-Data-Fusion

Laserscanner Based Cooperative Pre-Data-Fusion Laserscanner Based Cooperative Pre-Data-Fusion 63 Laserscanner Based Cooperative Pre-Data-Fusion F. Ahlers, Ch. Stimming, Ibeo Automobile Sensor GmbH Abstract The Cooperative Pre-Data-Fusion is a novel

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

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

Seminar Dept. Automação e Sistemas - UFSC Scan-to-Map Matching Using the Hausdorff Distance for Robust Mobile Robot Localization

Seminar Dept. Automação e Sistemas - UFSC Scan-to-Map Matching Using the Hausdorff Distance for Robust Mobile Robot Localization Seminar Dept. Automação e Sistemas - UFSC Scan-to-Map Matching Using the Hausdorff Distance for Robust Mobile Robot Localization Work presented at ICRA 2008, jointly with ANDRES GUESALAGA PUC Chile Miguel

More information

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

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

More information

Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot

Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot Yoichi Nakaguro Sirindhorn International Institute of Technology, Thammasat University P.O. Box 22, Thammasat-Rangsit Post Office,

More information

DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER

DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER S17- DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER Fumihiro Inoue 1 *, Takeshi Sasaki, Xiangqi Huang 3, and Hideki Hashimoto 4 1 Technica Research Institute,

More information

Introduction to Multi-Agent Programming

Introduction to Multi-Agent Programming Introduction to Multi-Agent Programming 6. Cooperative Sensing Modeling Sensors, Kalman Filter, Markov Localization, Potential Fields Alexander Kleiner, Bernhard Nebel Contents Introduction Modeling and

More information

Fusion Between Laser and Stereo Vision Data For Moving Objects Tracking In Intersection Like Scenario

Fusion Between Laser and Stereo Vision Data For Moving Objects Tracking In Intersection Like Scenario Fusion Between Laser and Stereo Vision Data For Moving Objects Tracking In Intersection Like Scenario Qadeer Baig, Olivier Aycard, Trung Dung Vu and Thierry Fraichard Abstract Using multiple sensors in

More information

Array Shape Tracking Using Active Sonar Reverberation

Array Shape Tracking Using Active Sonar Reverberation Lincoln Laboratory ASAP-2003 Worshop Array Shape Tracing Using Active Sonar Reverberation Vijay Varadarajan and Jeffrey Kroli Due University Department of Electrical and Computer Engineering Durham, NC

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

DYNAMIC POSITIONING OF A MOBILE ROBOT USING A LASER-BASED GONIOMETER. Joaquim A. Batlle*, Josep Maria Font*, Josep Escoda**

DYNAMIC POSITIONING OF A MOBILE ROBOT USING A LASER-BASED GONIOMETER. Joaquim A. Batlle*, Josep Maria Font*, Josep Escoda** DYNAMIC POSITIONING OF A MOBILE ROBOT USING A LASER-BASED GONIOMETER Joaquim A. Batlle*, Josep Maria Font*, Josep Escoda** * Department of Mechanical Engineering Technical University of Catalonia (UPC)

More information

Building Reliable 2D Maps from 3D Features

Building Reliable 2D Maps from 3D Features Building Reliable 2D Maps from 3D Features Dipl. Technoinform. Jens Wettach, Prof. Dr. rer. nat. Karsten Berns TU Kaiserslautern; Robotics Research Lab 1, Geb. 48; Gottlieb-Daimler- Str.1; 67663 Kaiserslautern;

More information

Grid-Based Models for Dynamic Environments

Grid-Based Models for Dynamic Environments Grid-Based Models for Dynamic Environments Daniel Meyer-Delius Maximilian Beinhofer Wolfram Burgard Abstract The majority of existing approaches to mobile robot mapping assume that the world is, an assumption

More information

COMPARISON OF ROBOT NAVIGATION METHODS USING PERFORMANCE METRICS

COMPARISON OF ROBOT NAVIGATION METHODS USING PERFORMANCE METRICS COMPARISON OF ROBOT NAVIGATION METHODS USING PERFORMANCE METRICS Adriano Flores Dantas, Rodrigo Porfírio da Silva Sacchi, Valguima V. V. A. Odakura Faculdade de Ciências Exatas e Tecnologia (FACET) Universidade

More information

L10. PARTICLE FILTERING CONTINUED. NA568 Mobile Robotics: Methods & Algorithms

L10. PARTICLE FILTERING CONTINUED. NA568 Mobile Robotics: Methods & Algorithms L10. PARTICLE FILTERING CONTINUED NA568 Mobile Robotics: Methods & Algorithms Gaussian Filters The Kalman filter and its variants can only model (unimodal) Gaussian distributions Courtesy: K. Arras Motivation

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

AUTONOMOUS SYSTEMS. PROBABILISTIC LOCALIZATION Monte Carlo Localization

AUTONOMOUS SYSTEMS. PROBABILISTIC LOCALIZATION Monte Carlo Localization AUTONOMOUS SYSTEMS PROBABILISTIC LOCALIZATION Monte Carlo Localization Maria Isabel Ribeiro Pedro Lima With revisions introduced by Rodrigo Ventura Instituto Superior Técnico/Instituto de Sistemas e Robótica

More information

This chapter explains two techniques which are frequently used throughout

This chapter explains two techniques which are frequently used throughout Chapter 2 Basic Techniques This chapter explains two techniques which are frequently used throughout this thesis. First, we will introduce the concept of particle filters. A particle filter is a recursive

More information

MULTI-ROBOT research has gained a broad attention. A Novel Way to Implement Self-localization in a Multi-robot Experimental Platform

MULTI-ROBOT research has gained a broad attention. A Novel Way to Implement Self-localization in a Multi-robot Experimental Platform 21 American Control Conference Marriott Waterfront, Baltimore, MD, USA June 3-July 2, 21 FrC16.5 A Novel Way to Implement Self-localization in a Multi-robot Experimental Platform Sheng Zhao and Manish

More information

Probabilistic Robotics

Probabilistic Robotics Probabilistic Robotics Bayes Filter Implementations Discrete filters, Particle filters Piecewise Constant Representation of belief 2 Discrete Bayes Filter Algorithm 1. Algorithm Discrete_Bayes_filter(

More information

REFINEMENT OF COLORED MOBILE MAPPING DATA USING INTENSITY IMAGES

REFINEMENT OF COLORED MOBILE MAPPING DATA USING INTENSITY IMAGES REFINEMENT OF COLORED MOBILE MAPPING DATA USING INTENSITY IMAGES T. Yamakawa a, K. Fukano a,r. Onodera a, H. Masuda a, * a Dept. of Mechanical Engineering and Intelligent Systems, The University of Electro-Communications,

More information

NERC Gazebo simulation implementation

NERC Gazebo simulation implementation NERC 2015 - Gazebo simulation implementation Hannan Ejaz Keen, Adil Mumtaz Department of Electrical Engineering SBA School of Science & Engineering, LUMS, Pakistan {14060016, 14060037}@lums.edu.pk ABSTRACT

More information

OpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps

OpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps OpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps Georgios Floros, Benito van der Zander and Bastian Leibe RWTH Aachen University, Germany http://www.vision.rwth-aachen.de floros@vision.rwth-aachen.de

More information

CSE 490R P1 - Localization using Particle Filters Due date: Sun, Jan 28-11:59 PM

CSE 490R P1 - Localization using Particle Filters Due date: Sun, Jan 28-11:59 PM CSE 490R P1 - Localization using Particle Filters Due date: Sun, Jan 28-11:59 PM 1 Introduction In this assignment you will implement a particle filter to localize your car within a known map. This will

More information

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods Prof. Daniel Cremers 11. Sampling Methods Sampling Methods Sampling Methods are widely used in Computer Science as an approximation of a deterministic algorithm to represent uncertainty without a parametric

More information

Dealing with Scale. Stephan Weiss Computer Vision Group NASA-JPL / CalTech

Dealing with Scale. Stephan Weiss Computer Vision Group NASA-JPL / CalTech Dealing with Scale Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline Why care about size? The IMU as scale provider: The

More information

A High Dynamic Range Vision Approach to Outdoor Localization

A High Dynamic Range Vision Approach to Outdoor Localization A High Dynamic Range Vision Approach to Outdoor Localization Kiyoshi Irie, Tomoaki Yoshida, and Masahiro Tomono Abstract We propose a novel localization method for outdoor mobile robots using High Dynamic

More information

Grid-based Localization and Online Mapping with Moving Objects Detection and Tracking: new results

Grid-based Localization and Online Mapping with Moving Objects Detection and Tracking: new results Grid-based Localization and Online Mapping with Moving Objects Detection and Tracking: new results Trung-Dung Vu, Julien Burlet and Olivier Aycard Laboratoire d Informatique de Grenoble, France firstname.lastname@inrialpes.fr

More information

Adapting the Sample Size in Particle Filters Through KLD-Sampling

Adapting the Sample Size in Particle Filters Through KLD-Sampling Adapting the Sample Size in Particle Filters Through KLD-Sampling Dieter Fox Department of Computer Science & Engineering University of Washington Seattle, WA 98195 Email: fox@cs.washington.edu Abstract

More information

RBMCDAbox - Matlab Toolbox of Rao-Blackwellized Data Association Particle Filters

RBMCDAbox - Matlab Toolbox of Rao-Blackwellized Data Association Particle Filters RBMCDAbox - Matlab Toolbox of Rao-Blacwellized Data Association Particle Filters Jouni Hartiainen and Simo Särä Department of Biomedical Engineering and Computational Science, Helsini University of Technology,

More information

Particle Filters. CSE-571 Probabilistic Robotics. Dependencies. Particle Filter Algorithm. Fast-SLAM Mapping

Particle Filters. CSE-571 Probabilistic Robotics. Dependencies. Particle Filter Algorithm. Fast-SLAM Mapping CSE-571 Probabilistic Robotics Fast-SLAM Mapping Particle Filters Represent belief by random samples Estimation of non-gaussian, nonlinear processes Sampling Importance Resampling (SIR) principle Draw

More information

`On a Tracking Scheme with Probabilistic Completeness for a Distributed Sensor Network

`On a Tracking Scheme with Probabilistic Completeness for a Distributed Sensor Network `On a Tracing Scheme with Probabilistic Completeness for a Distributed Sensor Networ K Madhava Krishna Henry Hexmoor Dept. of Computer Science and Computer Engineering University of Aransas Fayetteville,

More information

A New Omnidirectional Vision Sensor for Monte-Carlo Localization

A New Omnidirectional Vision Sensor for Monte-Carlo Localization A New Omnidirectional Vision Sensor for Monte-Carlo Localization E. Menegatti 1, A. Pretto 1, and E. Pagello 12 1 Intelligent Autonomous Systems Laboratory Department of Information Engineering The University

More information

5. Tests and results Scan Matching Optimization Parameters Influence

5. Tests and results Scan Matching Optimization Parameters Influence 126 5. Tests and results This chapter presents results obtained using the proposed method on simulated and real data. First, it is analyzed the scan matching optimization; after that, the Scan Matching

More information

First scan matching algorithms. Alberto Quattrini Li University of South Carolina

First scan matching algorithms. Alberto Quattrini Li University of South Carolina First scan matching algorithms Alberto Quattrini Li 2015-10-22 University of South Carolina Robot mapping through scan-matching Framework for consistent registration of multiple frames of measurements

More information

3D Sensing and Mapping for a Tracked Mobile Robot with a Movable Laser Ranger Finder

3D Sensing and Mapping for a Tracked Mobile Robot with a Movable Laser Ranger Finder 3D Sensing and Mapping for a Tracked Mobile Robot with a Movable Laser Ranger Finder Toyomi Fujita Abstract This paper presents a sensing system for 3D sensing and mapping by a tracked mobile robot with

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

Localization, Mapping and Exploration with Multiple Robots. Dr. Daisy Tang

Localization, Mapping and Exploration with Multiple Robots. Dr. Daisy Tang Localization, Mapping and Exploration with Multiple Robots Dr. Daisy Tang Two Presentations A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping, by Thrun, Burgard

More information

Floor Sensing System Using Laser Range Finder and Mirror for Localizing Daily Life Commodities

Floor Sensing System Using Laser Range Finder and Mirror for Localizing Daily Life Commodities The 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems October 18-22, 2010, Taipei, Taiwan Floor Sensing System Using Laser Range Finder and for Localizing Daily Life Commodities

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

Ensemble of Bayesian Filters for Loop Closure Detection

Ensemble of Bayesian Filters for Loop Closure Detection Ensemble of Bayesian Filters for Loop Closure Detection Mohammad Omar Salameh, Azizi Abdullah, Shahnorbanun Sahran Pattern Recognition Research Group Center for Artificial Intelligence Faculty of Information

More information

REMARKS ON MARKERLESS HUMAN MOTION CAPTURE USING MULTIPLE IMAGES OF 3D ARTICULATED HUMAN CG MODEL

REMARKS ON MARKERLESS HUMAN MOTION CAPTURE USING MULTIPLE IMAGES OF 3D ARTICULATED HUMAN CG MODEL 18th European Signal Processing Conference (EUSIPCO-2010) Aalborg, Denmar, August 23-27, 2010 REMARKS ON MARKERLESS HUMAN MOTION CAPTURE USING MULTIPLE IMAGES OF 3D ARTICULATED HUMAN CG MODEL Kazuhio Taahashi

More information

Three-Dimensional Measurement of Objects in Liquid with an Unknown Refractive Index Using Fisheye Stereo Camera

Three-Dimensional Measurement of Objects in Liquid with an Unknown Refractive Index Using Fisheye Stereo Camera Three-Dimensional Measurement of Objects in Liquid with an Unknown Refractive Index Using Fisheye Stereo Camera Kazuki Sakamoto, Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, and Hajime Asama Abstract

More information

Odometry-based Online Extrinsic Sensor Calibration

Odometry-based Online Extrinsic Sensor Calibration 213 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) November 3-7, 213. Toyo, Japan Odometry-based Online Extrinsic Sensor Calibration Sebastian Schneider, Thorsten Luettel and

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

The UTIAS multi-robot cooperative localization and mapping dataset

The UTIAS multi-robot cooperative localization and mapping dataset The UTIAS multi-robot cooperative localization and mapping dataset The International Journal of Robotics Research 30(8) 969 974 The Author(s) 2011 Reprints and permission: sagepub.co.uk/journalspermissions.nav

More information

UAV Autonomous Navigation in a GPS-limited Urban Environment

UAV Autonomous Navigation in a GPS-limited Urban Environment UAV Autonomous Navigation in a GPS-limited Urban Environment Yoko Watanabe DCSD/CDIN JSO-Aerial Robotics 2014/10/02-03 Introduction 2 Global objective Development of a UAV onboard system to maintain flight

More information

Robot Simultaneous Localization and Mapping Based on Self-Detected Waypoint

Robot Simultaneous Localization and Mapping Based on Self-Detected Waypoint BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 2 Sofia 2016 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.1515/cait-2016-0031 Robot Simultaneous Localization

More information

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Wolfram Burgard 1 Motivation Recall: Discrete filter Discretize the continuous state space High memory complexity

More information

Generalizing Random-Vector SLAM with Random Finite Sets

Generalizing Random-Vector SLAM with Random Finite Sets Generalizing Random-Vector SLAM with Random Finite Sets Keith Y. K. Leung, Felipe Inostroza, Martin Adams Advanced Mining Technology Center AMTC, Universidad de Chile, Santiago, Chile eith.leung@amtc.uchile.cl,

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

Fusion of Radar and EO-sensors for Surveillance

Fusion of Radar and EO-sensors for Surveillance of Radar and EO-sensors for Surveillance L.J.H.M. Kester, A. Theil TNO Physics and Electronics Laboratory P.O. Box 96864, 2509 JG The Hague, The Netherlands kester@fel.tno.nl, theil@fel.tno.nl Abstract

More information

The Internet of Things: Roadmap to a Connected World. IoT and Localization

The Internet of Things: Roadmap to a Connected World. IoT and Localization IoT and Localization Daniela Rus Andrew (1956) and Erna Viterbi Prof., EECS Director, CSAIL Computer Science and Artificial Intelligence Laboratory (CSAIL) Massachusetts Institute of Technology 4x 4x

More information

Model-based segmentation and recognition from range data

Model-based segmentation and recognition from range data Model-based segmentation and recognition from range data Jan Boehm Institute for Photogrammetry Universität Stuttgart Germany Keywords: range image, segmentation, object recognition, CAD ABSTRACT This

More information

A Framework for Bearing-Only Sparse Semantic Self-Localization for Visually Impaired People

A Framework for Bearing-Only Sparse Semantic Self-Localization for Visually Impaired People A Framework for Bearing-Only Sparse Semantic Self-Localization for Visually Impaired People Irem Uygur, Renato Miyagusuku, Sarthak Pathak, Alessandro Moro, Atsushi Yamashita, and Hajime Asama Abstract

More information

CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING

CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING Kenta Fukano 1, and Hiroshi Masuda 2 1) Graduate student, Department of Intelligence Mechanical Engineering, The University of Electro-Communications,

More information

People Tracking for Enabling Human-Robot Interaction in Large Public Spaces

People Tracking for Enabling Human-Robot Interaction in Large Public Spaces Dražen Brščić University of Rijeka, Faculty of Engineering http://www.riteh.uniri.hr/~dbrscic/ People Tracking for Enabling Human-Robot Interaction in Large Public Spaces This work was largely done at

More information