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

Size: px
Start display at page:

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

Transcription

1 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 Mellon University Pittsburgh, Pennsylvania c Carnegie Mellon University

2 1 Introduction Current outdoor localization methods are heavily dependent on accurate pose estimation in the form of GPS and inertial measurement. However, GPS technology is limited in accuracy and depends on unobstructed views of the sky, and inertial measurement systems tolerant of outdoor driving conditions are very expensive. We attempt to localize the pose of a robotic ground vehicle using only unreliable vehicle speed estimates and a high-speed 3D laser scanner. Furthermore, while most localization systems use a-priori maps generated by other ground sensors, we use a map generated from aerial lidar. 1.1 Dataset The primary vehicle data set consists of the sensor measurements collected from a Velodyne lidar. This lidar unit generates 2.5 million range measurements per second, sampling a full 360 degrees around the system. This information is provided as a sequence of log files containing timestamped point sets in 3D Cartesian coordinates referenced from an origin at the Velodyne sensor. We collected this data using the autonomous ground vehicle Boss, which sports a single, roof-mounted Velodyne lidar as part of a wide array of navigational sensors, as seen in Figure 1. Most importantly, its sensor suite includes differential GPS and inertial measurement, providing us with accurate ground truth data. Figure 1: Boss, the autonomous ground vehicle Figure 2 shows a part of the Robot City road network. We drove Boss around the edge of this network, using the trail depicted by the thick white arrows in the figure. Our data set consists of seconds of Velodyne measurements and ground truth vehicle state logged during this run. We also obtained a map of Robot City in the form of a registered point set taken from aerial lidar, using the aerial platform in Figure 3(b). The map, as seen in Figure 4, consists of over 11 million 3D Cartesian points scattered across the site. The points cover the site with a density approximating 10cm spatial resolution. 2 Monte Carlo Localization 2.1 Monte Carlo Localization Monte Carlo Localization (MCL) is a sampling-based localization method for approximating probability density distributions [1, 2]. In this method, the variable of interest, x t, is represented by a probability density. In localization problems, the variable of interest is often referred to as the state. In our case, the state is the expected pose of the robotic vehicle, x t =< x t, y t, θ t > T. In an MCL, an individual state is considered to be complete because the Markov assumption asserts that all previous experience (e.g., past sensor measurements) is independent of future experience given the current experience [2]. Since we assume that the pose information is not measurable directly and accurately, a localization process must involve some form of inference. We need to represent our belief over possible poses as conditional probability distri- I

3 Figure 2: Road network at Robot City (a) Scanning equipment (b) Equipment on helicopter Figure 3: Scanning platform used to generate aerial lidar map butions. MCL represents this belief distribution as a population of particles that are propagated each timestep. The density of the particles approximates the belief distribution over the state space. Given a motion model u t, a belief on the previous state belief(x t 1 ) can be used to predict a possible new state, belief(x t ). belief(x t ) = p(x t u t, x t 1 )belief(x t 1 )dx t 1 These predicted states, belief(x t ), are evaluated by a sensor measurement model z t, II

4 Figure 4: Lidar point set of Robot City belief(x t ) = ηp(z t x t )belief(x t ) This is simply a Bayes filter. The MCL integrates this Bayes filter with a particle filter to form a localization process. Algorithm 1 provides the details of the basic MCL process in pseudocode [1]. Algorithm 1 MCL(X t 1, u t, z t, m) X t = X t = 0 for m = 1 to M do x m t = MOTIONMODEL(u t, x m t 1) wt m = MEASUREMENTMODEL(z t, x m t, m) X t = X t + < x m t, wt m > end for for m = 1 to M do draw i with probability w i t add x i t to X t end for return X t 2.2 Implementation and Results Our implementation of MCL follows fairly closely to the basic pseudocode outline. For the motion model, we used our knowledge of the vehicle to create a reasonable planar unicycle approximation. The vehicle speed estimate from our ground truth data with an added Gaussian noise term was our control input. The steering curvature was sampled uniformly between the vehicle steering limits. This seemed to adequately represent the vehicle s movement in our dataset. However, there were significant design decisions to be made in the implementation of the measurement model. The first issue we faced in implementing MCL in this system was in the dimensionality of the data. Both the velodyne data and the map are 3D point sets, meaning that a 6DOF transform is necessary to convert from the velodyne reference frame to the world frame. However, we examined the vehicle state log files and determined that the vast majority of the time, the vehicle was close to vertical. Thus, we could simplify the state to the vector < x t, y t, θ t > T, and use constant offsets based on the vehicle configuration to create an appropriate tranformation matrix. The primary issue, however, turned out to be the computational complexity of the scan matching problem. The Velodyne log files for our dataset alone consume 2.5Gb of disk space. The map consumes 173Mb in its compressed form. In addition, because our state space would be tested by matching points in higher-dimensional world space, we hypothesized that a large number of particles would be necessary to achieve sufficient sampling density. This limited the approaches we could take to functions that could be executed very quickly on very large point sets. We settled upon two approaches, a nearest-neighbor based distance metric, and a height-based distance metric. III

5 Min Max Mean σ Table 1: Error metrics for sample run KD-Tree Our first measurement model transformed the velodyne data to world coordinates, then searched for the nearest neighbor to that point using a free Matlab kd-tree package. 1 The error for each point was the L2-norm distance from the point to its nearest neighbor. The error for each particle was simply the sum of these point errors Height Map Our second measurement model similarly transformed the velodyne data, but then matched the points against the height at their < x t, y t > T location. The error for each point was then the squared difference in height between the point and the height map. The error for each particle was once again the sum of these point errors. For both methods, the reciprocal of the error was used as the particle weight. As specified in the MCL algorithm, it was used as an unnormalized mass function to sample the next generation of particles. A sample of this matching can be seen in Figure 5. Figure 5: Matching Velodyne scans to the map Much of our original dataset was not usable due to a lack of visible obstacles in the velodyne data. We selected a subset of the data, and conducted sample runs along it using both distance estimation methods. The results can be seen in Figure 6, and the error information is shown in Figure 7 and Table 1. 3 Discussion Initially, we had hoped to do global localization by initializing the particle filter with particles sampled from locations along the road network. We were able to implement this using rejection sampling over a set of polygons encompassing the road network. However, when we began testing, it became clear that the point density required to find and track the vehicle would require us to initialize the particle filter with an exorbitant particle count, almost certainly in the several thousands. This would have been far too expensive to compute, so we ended up seeding the filter with the initial state recorded by the ground truth sensors. We also found one unexpected effect that hindered the performance of our MCL implementation. The Velodyne data was sampled uniformly in angular units, but the wide elevation range of the scan translated to very uneven 1 Michael, Steven; MIT Lincoln Labs; KD Tree Nearest Neighbor and Range Search IV

6 (a) Kd-tree MCL - best particles (red points) and ground truth (blue line) (b) Kd-tree MCL - all particles (points) and ground truth (blue line) (c) Height map MCL - all particles (points) and ground truth (blue line) Figure 6: Results of sample run using kd-tree and height map MCL sampling in Cartesian units. Points were heavily concentrated near and under the vehicle, biasing the error function toward favoring particles that placed the vehicle on flat ground rather than particles that matched more distant features. We tried uniformly resampling the points using interpolation and masking out nearby points from being evaluated by the error function, but neither were ideal, and neither completely resolved the issue. In comparing the performance of the two distance-finding strategies, kd-tree and height maps, we also found that while the height maps performed much faster and could handle 20 times more particles than the kd-tree search, the kd-tree performed significantly more accurately than the height map in both locating and tracking the vehicle pose. This is evident in Figure 6(a). It is likely that the 2 1 2D volumetric representation that the height map used did not match well against individual points, but would still perform well if used in conjunction with true ray-casting, which we did not attempt here. Also, the height map was significantly lower resolution than the original map, so it is possible that details represented in the Velodyne point sets were not represented properly in the height map distance. If you wish to see more, full size images and videos of our MCL in action are available at: pkv/movies. V

7 7 6 5 Error(m) Step Figure 7: MCL error during sample run VI

8 References [1] D. Fox, W. Burgard, F. Dellaert, and S. Thrun. Monte carlo localization: Efficient position estimation for mobile robots. In Proceedings of the Sixteenth National Conference on Artificial Intelligence, pages , [2] S. Thrun, W. Burgard, and D. Fox. Probabilistic Robotics. MIT Press, VII

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

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

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

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

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

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

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

Monte Carlo Localization using Dynamically Expanding Occupancy Grids. Karan M. Gupta

Monte Carlo Localization using Dynamically Expanding Occupancy Grids. Karan M. Gupta 1 Monte Carlo Localization using Dynamically Expanding Occupancy Grids Karan M. Gupta Agenda Introduction Occupancy Grids Sonar Sensor Model Dynamically Expanding Occupancy Grids Monte Carlo Localization

More information

Mapping Contoured Terrain Using SLAM with a Radio- Controlled Helicopter Platform. Project Proposal. Cognitive Robotics, Spring 2005

Mapping Contoured Terrain Using SLAM with a Radio- Controlled Helicopter Platform. Project Proposal. Cognitive Robotics, Spring 2005 Mapping Contoured Terrain Using SLAM with a Radio- Controlled Helicopter Platform Project Proposal Cognitive Robotics, Spring 2005 Kaijen Hsiao Henry de Plinval Jason Miller Introduction In the context

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

Robotics. Lecture 5: Monte Carlo Localisation. See course website for up to date information.

Robotics. Lecture 5: Monte Carlo Localisation. See course website  for up to date information. Robotics Lecture 5: Monte Carlo Localisation See course website http://www.doc.ic.ac.uk/~ajd/robotics/ for up to date information. Andrew Davison Department of Computing Imperial College London Review:

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

Scan Matching. Pieter Abbeel UC Berkeley EECS. Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics

Scan Matching. Pieter Abbeel UC Berkeley EECS. Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics Scan Matching Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics Scan Matching Overview Problem statement: Given a scan and a map, or a scan and a scan,

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

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

Monte Carlo Localization for Mobile Robots

Monte Carlo Localization for Mobile Robots Monte Carlo Localization for Mobile Robots Frank Dellaert 1, Dieter Fox 2, Wolfram Burgard 3, Sebastian Thrun 4 1 Georgia Institute of Technology 2 University of Washington 3 University of Bonn 4 Carnegie

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

Domain Adaptation For Mobile Robot Navigation

Domain Adaptation For Mobile Robot Navigation Domain Adaptation For Mobile Robot Navigation David M. Bradley, J. Andrew Bagnell Robotics Institute Carnegie Mellon University Pittsburgh, 15217 dbradley, dbagnell@rec.ri.cmu.edu 1 Introduction An important

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

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

Sensory Augmentation for Increased Awareness of Driving Environment

Sensory Augmentation for Increased Awareness of Driving Environment Sensory Augmentation for Increased Awareness of Driving Environment Pranay Agrawal John M. Dolan Dec. 12, 2014 Technologies for Safe and Efficient Transportation (T-SET) UTC The Robotics Institute Carnegie

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

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

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

Artificial Intelligence for Robotics: A Brief Summary

Artificial Intelligence for Robotics: A Brief Summary Artificial Intelligence for Robotics: A Brief Summary This document provides a summary of the course, Artificial Intelligence for Robotics, and highlights main concepts. Lesson 1: Localization (using Histogram

More information

Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines

Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines Thomas Röfer 1, Tim Laue 1, and Dirk Thomas 2 1 Center for Computing Technology (TZI), FB 3, Universität Bremen roefer@tzi.de,

More information

Robust Monte-Carlo Localization using Adaptive Likelihood Models

Robust Monte-Carlo Localization using Adaptive Likelihood Models Robust Monte-Carlo Localization using Adaptive Likelihood Models Patrick Pfaff 1, Wolfram Burgard 1, and Dieter Fox 2 1 Department of Computer Science, University of Freiburg, Germany, {pfaff,burgard}@informatik.uni-freiburg.de

More information

Calibration of a rotating multi-beam Lidar

Calibration of a rotating multi-beam Lidar The 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems October 18-22, 2010, Taipei, Taiwan Calibration of a rotating multi-beam Lidar Naveed Muhammad 1,2 and Simon Lacroix 1,2 Abstract

More information

AUTONOMOUS SYSTEMS. LOCALIZATION, MAPPING & SIMULTANEOUS LOCALIZATION AND MAPPING Part V Mapping & Occupancy Grid Mapping

AUTONOMOUS SYSTEMS. LOCALIZATION, MAPPING & SIMULTANEOUS LOCALIZATION AND MAPPING Part V Mapping & Occupancy Grid Mapping AUTONOMOUS SYSTEMS LOCALIZATION, MAPPING & SIMULTANEOUS LOCALIZATION AND MAPPING Part V Mapping & Occupancy Grid Mapping Maria Isabel Ribeiro Pedro Lima with revisions introduced by Rodrigo Ventura Instituto

More information

Spring Localization II. Roland Siegwart, Margarita Chli, Martin Rufli. ASL Autonomous Systems Lab. Autonomous Mobile Robots

Spring Localization II. Roland Siegwart, Margarita Chli, Martin Rufli. ASL Autonomous Systems Lab. Autonomous Mobile Robots Spring 2016 Localization II Localization I 25.04.2016 1 knowledge, data base mission commands Localization Map Building environment model local map position global map Cognition Path Planning path Perception

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

Omnidirectional vision for robot localization in urban environments

Omnidirectional vision for robot localization in urban environments Omnidirectional vision for robot localization in urban environments Emanuele Frontoni, Andrea Ascani, Adriano Mancini, Primo Zingaretti Università Politecnica delle Marche Dipartimento di Ingegneria Informatica

More information

Probabilistic Robotics

Probabilistic Robotics Probabilistic Robotics Sebastian Thrun Wolfram Burgard Dieter Fox The MIT Press Cambridge, Massachusetts London, England Preface xvii Acknowledgments xix I Basics 1 1 Introduction 3 1.1 Uncertainty in

More information

Particle Filter in Brief. Robot Mapping. FastSLAM Feature-based SLAM with Particle Filters. Particle Representation. Particle Filter Algorithm

Particle Filter in Brief. Robot Mapping. FastSLAM Feature-based SLAM with Particle Filters. Particle Representation. Particle Filter Algorithm Robot Mapping FastSLAM Feature-based SLAM with Particle Filters Cyrill Stachniss Particle Filter in Brief! Non-parametric, recursive Bayes filter! Posterior is represented by a set of weighted samples!

More information

Mobile Robot Mapping and Localization in Non-Static Environments

Mobile Robot Mapping and Localization in Non-Static Environments Mobile Robot Mapping and Localization in Non-Static Environments Cyrill Stachniss Wolfram Burgard University of Freiburg, Department of Computer Science, D-790 Freiburg, Germany {stachnis burgard @informatik.uni-freiburg.de}

More information

Monte Carlo Localization using 3D Texture Maps

Monte Carlo Localization using 3D Texture Maps Monte Carlo Localization using 3D Texture Maps Yu Fu, Stephen Tully, George Kantor, and Howie Choset Abstract This paper uses KLD-based (Kullback-Leibler Divergence) Monte Carlo Localization (MCL) to localize

More information

Proprioceptive Localization for Mobile Manipulators

Proprioceptive Localization for Mobile Manipulators Carnegie Mellon University Research Showcase @ CMU Robotics Institute School of Computer Science 2-2010 Proprioceptive Localization for Mobile Manipulators Mehmet R. Dogar Carnegie Mellon University Vishal

More information

Spring Localization II. Roland Siegwart, Margarita Chli, Juan Nieto, Nick Lawrance. ASL Autonomous Systems Lab. Autonomous Mobile Robots

Spring Localization II. Roland Siegwart, Margarita Chli, Juan Nieto, Nick Lawrance. ASL Autonomous Systems Lab. Autonomous Mobile Robots Spring 2018 Localization II Localization I 16.04.2018 1 knowledge, data base mission commands Localization Map Building environment model local map position global map Cognition Path Planning path Perception

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

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

Robot Mapping. SLAM Front-Ends. Cyrill Stachniss. Partial image courtesy: Edwin Olson 1

Robot Mapping. SLAM Front-Ends. Cyrill Stachniss. Partial image courtesy: Edwin Olson 1 Robot Mapping SLAM Front-Ends Cyrill Stachniss Partial image courtesy: Edwin Olson 1 Graph-Based SLAM Constraints connect the nodes through odometry and observations Robot pose Constraint 2 Graph-Based

More information

POINT CLOUD ANALYSIS FOR ROAD PAVEMENTS IN BAD CONDITIONS INTRODUCTION

POINT CLOUD ANALYSIS FOR ROAD PAVEMENTS IN BAD CONDITIONS INTRODUCTION POINT CLOUD ANALYSIS FOR ROAD PAVEMENTS IN BAD CONDITIONS Yoshiyuki Yamamoto, Associate Professor Yasuhiro Shimizu, Doctoral Student Eiji Nakamura, Professor Masayuki Okugawa, Associate Professor Aichi

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

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

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

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

Active Monte Carlo Localization in Outdoor Terrains using Multi-Level Surface Maps

Active Monte Carlo Localization in Outdoor Terrains using Multi-Level Surface Maps Active Monte Carlo Localization in Outdoor Terrains using Multi-Level Surface Maps Rainer Kümmerle 1, Patrick Pfaff 1, Rudolph Triebel 2, and Wolfram Burgard 1 1 Department of Computer Science, University

More information

Efficient L-Shape Fitting for Vehicle Detection Using Laser Scanners

Efficient L-Shape Fitting for Vehicle Detection Using Laser Scanners Efficient L-Shape Fitting for Vehicle Detection Using Laser Scanners Xiao Zhang, Wenda Xu, Chiyu Dong, John M. Dolan, Electrical and Computer Engineering, Carnegie Mellon University Robotics Institute,

More information

Localization and Mapping in Urban Environments Using Mobile Robots

Localization and Mapping in Urban Environments Using Mobile Robots Denis F. Wolf 1 and Gaurav S. Sukhatme 2 1 Department Computer Systems Institute of Mathematics and Computer Science University of São Paulo P.O.Box 668, Zip 13560-970 São Carlos SP - BRAZIL denis@icmc.usp.br

More information

Probabilistic Robotics

Probabilistic Robotics Probabilistic Robotics Discrete Filters and Particle Filters Models Some slides adopted from: Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Kai Arras and Probabilistic Robotics Book SA-1 Probabilistic

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

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

PacSLAM Arunkumar Byravan, Tanner Schmidt, Erzhuo Wang

PacSLAM Arunkumar Byravan, Tanner Schmidt, Erzhuo Wang PacSLAM Arunkumar Byravan, Tanner Schmidt, Erzhuo Wang Project Goals The goal of this project was to tackle the simultaneous localization and mapping (SLAM) problem for mobile robots. Essentially, the

More information

Introduction to Mobile Robotics SLAM Landmark-based FastSLAM

Introduction to Mobile Robotics SLAM Landmark-based FastSLAM Introduction to Mobile Robotics SLAM Landmark-based FastSLAM Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello Partial slide courtesy of Mike Montemerlo 1 The SLAM Problem

More information

Monte Carlo Localization

Monte Carlo Localization Monte Carlo Localization P. Hiemstra & A. Nederveen August 24, 2007 Abstract In this paper we investigate robot localization with the Augmented Monte Carlo Localization (amcl) algorithm. The goal of the

More information

A Unified 3D Mapping Framework using a 3D or 2D LiDAR

A Unified 3D Mapping Framework using a 3D or 2D LiDAR A Unified 3D Mapping Framework using a 3D or 2D LiDAR Weikun Zhen and Sebastian Scherer Abstract Simultaneous Localization and Mapping (SLAM) has been considered as a solved problem thanks to the progress

More information

3D Convolutional Neural Networks for Landing Zone Detection from LiDAR

3D Convolutional Neural Networks for Landing Zone Detection from LiDAR 3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping

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

Probabilistic Matching for 3D Scan Registration

Probabilistic Matching for 3D Scan Registration Probabilistic Matching for 3D Scan Registration Dirk Hähnel Wolfram Burgard Department of Computer Science, University of Freiburg, 79110 Freiburg, Germany Abstract In this paper we consider the problem

More information

Scan-point Planning and 3-D Map Building for a 3-D Laser Range Scanner in an Outdoor Environment

Scan-point Planning and 3-D Map Building for a 3-D Laser Range Scanner in an Outdoor Environment Scan-point Planning and 3-D Map Building for a 3-D Laser Range Scanner in an Outdoor Environment Keiji NAGATANI 1, Takayuki Matsuzawa 1, and Kazuya Yoshida 1 Tohoku University Summary. During search missions

More information

Basics of Localization, Mapping and SLAM. Jari Saarinen Aalto University Department of Automation and systems Technology

Basics of Localization, Mapping and SLAM. Jari Saarinen Aalto University Department of Automation and systems Technology Basics of Localization, Mapping and SLAM Jari Saarinen Aalto University Department of Automation and systems Technology Content Introduction to Problem (s) Localization A few basic equations Dead Reckoning

More information

Path Planning with Dynamic Obstacle Avoidance for a Jumping-Enabled Robot

Path Planning with Dynamic Obstacle Avoidance for a Jumping-Enabled Robot Path Planning with Dynamic Obstacle Avoidance for a Jumping-Enabled Robot Peggy (Yuchun) Wang and Caitlin Hogan Department of Computer Science, Stanford University Robotic navigation is an important concern

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

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

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

F1/10 th Autonomous Racing. Localization. Nischal K N

F1/10 th Autonomous Racing. Localization. Nischal K N F1/10 th Autonomous Racing Localization Nischal K N System Overview Mapping Hector Mapping Localization Path Planning Control System Overview Mapping Hector Mapping Localization Adaptive Monte Carlo Localization

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

Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization

Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization Marcus A. Brubaker (Toyota Technological Institute at Chicago) Andreas Geiger (Karlsruhe Institute of Technology & MPI Tübingen) Raquel

More information

Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments. Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno

Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments. Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno Motivation Aerial robotic operation in GPS-denied Degraded

More information

What is the SLAM problem?

What is the SLAM problem? SLAM Tutorial Slides by Marios Xanthidis, C. Stachniss, P. Allen, C. Fermuller Paul Furgale, Margarita Chli, Marco Hutter, Martin Rufli, Davide Scaramuzza, Roland Siegwart What is the SLAM problem? The

More information

Evaluating the Performance of a Vehicle Pose Measurement System

Evaluating the Performance of a Vehicle Pose Measurement System Evaluating the Performance of a Vehicle Pose Measurement System Harry Scott Sandor Szabo National Institute of Standards and Technology Abstract A method is presented for evaluating the performance of

More information

Detection and Tracking of Moving Objects Using 2.5D Motion Grids

Detection and Tracking of Moving Objects Using 2.5D Motion Grids Detection and Tracking of Moving Objects Using 2.5D Motion Grids Alireza Asvadi, Paulo Peixoto and Urbano Nunes Institute of Systems and Robotics, University of Coimbra September 2015 1 Outline: Introduction

More information

arxiv: v2 [cs.ds] 7 Mar 2018

arxiv: v2 [cs.ds] 7 Mar 2018 : Fast Approximate 2D Ray Casting for Accelerated Localization arxiv:705.067v2 [cs.ds] 7 Mar 208 Corey H. Walsh and Sertac Karaman2 Abstract Localization is an essential component for autonomous robots.

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

Chapters 1 7: Overview

Chapters 1 7: Overview Chapters 1 7: Overview Photogrammetric mapping: introduction, applications, and tools GNSS/INS-assisted photogrammetric and LiDAR mapping LiDAR mapping: principles, applications, mathematical model, and

More information

High-Precision Positioning Unit 2.2 Student Exercise: Calculating Topographic Change

High-Precision Positioning Unit 2.2 Student Exercise: Calculating Topographic Change High-Precision Positioning Unit 2.2 Student Exercise: Calculating Topographic Change Ian Lauer and Ben Crosby (Idaho State University) Change is an inevitable part of our natural world and varies as a

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

Normal Distributions Transform Monte-Carlo Localization (NDT-MCL)

Normal Distributions Transform Monte-Carlo Localization (NDT-MCL) Normal Distributions Transform Monte-Carlo Localization (NDT-MCL) Jari Saarinen, Henrik Andreasson, Todor Stoyanov and Achim J. Lilienthal Abstract Industrial applications often impose hard requirements

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

Real Time Data Association for FastSLAM

Real Time Data Association for FastSLAM Real Time Data Association for FastSLAM Juan Nieto, Jose Guivant, Eduardo Nebot Australian Centre for Field Robotics, The University of Sydney, Australia fj.nieto,jguivant,nebotg@acfr.usyd.edu.au Sebastian

More information

Introduction to Mobile Robotics SLAM Grid-based FastSLAM. Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello

Introduction to Mobile Robotics SLAM Grid-based FastSLAM. Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello Introduction to Mobile Robotics SLAM Grid-based FastSLAM Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello 1 The SLAM Problem SLAM stands for simultaneous localization

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

L17. OCCUPANCY MAPS. NA568 Mobile Robotics: Methods & Algorithms

L17. OCCUPANCY MAPS. NA568 Mobile Robotics: Methods & Algorithms L17. OCCUPANCY MAPS NA568 Mobile Robotics: Methods & Algorithms Today s Topic Why Occupancy Maps? Bayes Binary Filters Log-odds Occupancy Maps Inverse sensor model Learning inverse sensor model ML map

More information

CANAL FOLLOWING USING AR DRONE IN SIMULATION

CANAL FOLLOWING USING AR DRONE IN SIMULATION CANAL FOLLOWING USING AR DRONE IN SIMULATION ENVIRONMENT Ali Ahmad, Ahmad Aneeque Khalid Department of Electrical Engineering SBA School of Science & Engineering, LUMS, Pakistan {14060006, 14060019}@lums.edu.pk

More information

APPENDIX E2. Vernal Pool Watershed Mapping

APPENDIX E2. Vernal Pool Watershed Mapping APPENDIX E2 Vernal Pool Watershed Mapping MEMORANDUM To: U.S. Fish and Wildlife Service From: Tyler Friesen, Dudek Subject: SSHCP Vernal Pool Watershed Analysis Using LIDAR Data Date: February 6, 2014

More information

Introduction to Mobile Robotics Probabilistic Motion Models

Introduction to Mobile Robotics Probabilistic Motion Models Introduction to Mobile Robotics Probabilistic Motion Models Wolfram Burgard, Michael Ruhnke, Bastian Steder 1 Robot Motion Robot motion is inherently uncertain. How can we model this uncertainty? Dynamic

More information

Final Exam Practice Fall Semester, 2012

Final Exam Practice Fall Semester, 2012 COS 495 - Autonomous Robot Navigation Final Exam Practice Fall Semester, 2012 Duration: Total Marks: 70 Closed Book 2 hours Start Time: End Time: By signing this exam, I agree to the honor code Name: Signature:

More information

Introduction to Mobile Robotics Techniques for 3D Mapping

Introduction to Mobile Robotics Techniques for 3D Mapping Introduction to Mobile Robotics Techniques for 3D Mapping Wolfram Burgard, Michael Ruhnke, Bastian Steder 1 Why 3D Representations Robots live in the 3D world. 2D maps have been applied successfully for

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

Neural Networks for Obstacle Avoidance

Neural Networks for Obstacle Avoidance Neural Networks for Obstacle Avoidance Joseph Djugash Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 josephad@andrew.cmu.edu Bradley Hamner Robotics Institute Carnegie Mellon University

More information

Statistical Techniques in Robotics (16-831, F12) Lecture#05 (Wednesday, September 12) Mapping

Statistical Techniques in Robotics (16-831, F12) Lecture#05 (Wednesday, September 12) Mapping Statistical Techniques in Robotics (16-831, F12) Lecture#05 (Wednesday, September 12) Mapping Lecturer: Alex Styler (in for Drew Bagnell) Scribe: Victor Hwang 1 1 Occupancy Mapping When solving the localization

More information

Autonomous Navigation of Humanoid Using Kinect. Harshad Sawhney Samyak Daga 11633

Autonomous Navigation of Humanoid Using Kinect. Harshad Sawhney Samyak Daga 11633 Autonomous Navigation of Humanoid Using Kinect Harshad Sawhney 11297 Samyak Daga 11633 Motivation Humanoid Space Missions http://www.buquad.com Motivation Disaster Recovery Operations http://www.designnews.com

More information

Aerial and Ground-based Collaborative Mapping: An Experimental Study

Aerial and Ground-based Collaborative Mapping: An Experimental Study Aerial and Ground-based Collaborative Mapping: An Experimental Study Ji Zhang and Sanjiv Singh Abstract We here present studies to enable aerial and ground-based collaborative mapping in GPS-denied environments.

More information

Team Description Paper Team AutonOHM

Team Description Paper Team AutonOHM Team Description Paper Team AutonOHM Jon Martin, Daniel Ammon, Helmut Engelhardt, Tobias Fink, Tobias Scholz, and Marco Masannek University of Applied Science Nueremberg Georg-Simon-Ohm, Kesslerplatz 12,

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

Testing omnidirectional vision-based Monte-Carlo Localization under occlusion

Testing omnidirectional vision-based Monte-Carlo Localization under occlusion Testing omnidirectional vision-based Monte-Carlo Localization under occlusion E. Menegatti, A. Pretto and E. Pagello Intelligent Autonomous Systems Laboratory Department of Information Engineering The

More information

Construction and Calibration of a Low-Cost 3D Laser Scanner with 360º Field of View for Mobile Robots

Construction and Calibration of a Low-Cost 3D Laser Scanner with 360º Field of View for Mobile Robots Construction and Calibration of a Low-Cost 3D Laser Scanner with 360º Field of View for Mobile Robots Jorge L. Martínez, Jesús Morales, Antonio, J. Reina, Anthony Mandow, Alejandro Pequeño-Boter*, and

More information

Introduction to Mobile Robotics

Introduction to Mobile Robotics Introduction to Mobile Robotics Gaussian Processes Wolfram Burgard Cyrill Stachniss Giorgio Grisetti Maren Bennewitz Christian Plagemann SS08, University of Freiburg, Department for Computer Science Announcement

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

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