Visual SLAM for small Unmanned Aerial Vehicles

Size: px
Start display at page:

Download "Visual SLAM for small Unmanned Aerial Vehicles"

Transcription

1 Visual SLAM for small Unmanned Aerial Vehicles Margarita Chli Autonomous Systems Lab, ETH Zurich

2 Simultaneous Localization And Mapping How can a body navigate in a previously unknown environment while constantly building and updating a map of its workspace using on board sensors only? One of the most challenging problems in probabilistic robotics Pure localization with a known map. SLAM: no a priori knowledge of the robot s workspace Mapping with known robot poses. SLAM: the robot poses have to be estimated along the way Robot localization using Satellite images [Senlet and Elgammal, ICRA 2012] Helicopter pose given by Leica tracker Video courtesy of S. Lynen 2

3 Integrated Components for Assisted Rescue and Unmanned Search operations IP running between , budget: 17 M, 24 partners Search-and-rescue combining robotics for land, sea and air ETHZ: map generation, people detection, from a UAV 3

4 4

5 How far are we from UAVs able to act as an aid in alpine search-and-rescue? Image source: 5

6 Small UAVs in SHERPA Sensor fusion for environment reconstruction & victim localization: IMU, visible light and thermal cameras, for robust SLAM Close collaboration with Club Alpino Italiano and the Swiss Institute for Avalanche Research 20m 6

7 AIRobots: Innovative aerial service robots for remote inspections by contact Aerial inspection of large industrial facilities Visual pre-inspection Inspection by contact (ultasonic probing) Reduce human involvement & outage periods Safety risks Costs ETH: onboard SLAM for navigation and control with custom-built sensor [Burri et al., CARPI 2012] 7

8 SLAM for small UAVs. Properties & Challenges Weight Lightweight & safe(r) easily deployable than larger aerial vehicles Limited payload (<500g): 10g need approx. 1W in hovering mode (rotor-wing) Limited computational power onboard Choose sensors with high information density Agility RW: highly agile (up to 8m/s) FW: max. 30m/s High-rate, real-time state estimation. The UAV cannot stop Fast, unstable dynamics Autonomy Low bandwidth/ unreliable data links onboard processing RW: Limited battery life (~10mins) FW: Solar powered (5-14hrs endurance) Platform dynamics RW: ROTOR-WING FW: FIXED-WING control speed 8

9 Single Camera SLAM Vision for SLAM Images = information-rich snapshots of a scene Cameras: compact + lightweight HW advances SLAM using a single camera: Hard but (e.g. cannot recover depth from 1 image) very applicable Image Courtesy of G. Klein 9

10 A glance over Monocular SLAM lit Can we track the motion of a camera while it is moving? Pick natural scene features to serve as landmarks (in most modern SLAM systems) Range sensing (laser/sonar): points, line segments, 3D planes, corners Vision: point features, lines, textured surfaces. Courtesy of A. Davison Key: features must be distinctive & recognizable from different viewpoints 10

11 MonoSLAM [Davison, ICCV 2003] Courtesy of A. Davison camera view internal SLAM map 11

12 Prominent Monocular SLAM systems MonoSLAM [Davison 2003 & Davison et al. 2007] PTAM [Klein, Murray 2007] Graph-SLAM [Eade, Drummond 2007] revolutionary in the Vision & Robotics communities, but not ready to leave the lab & perform everyday tasks 12

13 Challenges Fast motion Large scales Robustness Rich maps Low computation Sensor failures Handle larger amounts of data effectively Competing goals: PRECISION EFFICIENCY Key: agile manipulation of information 13

14 sfly: Swarm of micro flying robots aim: Fully autonomous small UAVs operating in unknown, cluttered environments, in a search-and-rescue scenario. 14

15 Enabling UAV navigation Task Autonomous UAV stabilization in GPS-denied environments Autonomous navigation and 3D mapping Long and sustained flights Approach Monocular visual-inertial navigation Downward-looking camera: bearing only measurements (monocular SLAM) IMU: Acceleration & angular velocity measurements Work with S. Weiss, M. Achtelik, S. Lynen and L. Kneip 15

16 Onboard visual SLAM (1 of 2) PTAM [Klein & Murray, ISMAR 2007] Keyframe-based SLAM for small, static scenes Tracking and mapping in separate threads Restrict no. keyframes visual odometry bigger drift Finest-scale features: most prone to outliers discarded from mapping but still crucial for tracking [Weiss et al., JFR 2013] 3D features camera pose pyramid levels Keyframe: typical outdoor scene 16

17 Onboard visual SLAM (2 of 2) [Weiss et al., JFR 2013] Tracking: Still track in finest pyramidal level Use AGAST corners Implementation ROS Package available Currently: ATOM 1.6GHz, 5 KFs: 20Hz Core2Duo 1.83 GHz, 15 KFs: 80 Hz (camera limitation), only using 1 core 17

18 Vision/IMU Controlled Flights [Achtelik et al., IROS 2012] 18

19 Vision-based UAV navigation First UAV system capable of vision-based flight in large real scenarios Framework used by NASA JPL, UPenn, MIT, TUM, What next? Extend capabilities for increased autonomy and deployability Follow-up directions: higher level tasks, exploit swarm and multi-robot behavior. Photo credits: Francois Pomerlaeu

20 BRISK: Binary Rotation Invariant Scalable Keypoints [ICCV 2011] Construct scale-space Image Pyramid Detect corners (FAST based) Assign scale to detected maxima Work with S. Leutenegger 20

21 BRISK: Binary Rotation Invariant Scalable Keypoints [ICCV 2011] BRIEF pattern for intensity pair samples generated randomly [Calonder et al., 2010] BRISK pattern: Used to access image values in a keypoint neighborhood Red circles: smoothing kernel applied. Scaled and rotated versions stored in a look-up table Pairwise intensity comparisons used for orientation assignment Binary Descriptor: a concatenation of pairwise comparison results BRISK sampling pattern 21

22 BRISK in action Precision-Recall: comparable to SIFT and SURF Detection and description ~10x faster than SURF Very fast matching using Hamming distance Open-source, BSD license Part of OpenCV 22

23 Tightly coupled visual-inertial SLAM (1 of 2) [RSS 2013] In-house developed sensor with hardware synchronized (stereo) camera & IMU Work on tight visual & inertial fusion: replace motion model with IMU constraints on the actual motion Vision-Only vs. Visual-Inertial Tight Fusion in Batch Optimization Many Landmarks Many Landmarks Pose Speed / biases Keypoint measurement IMU measurement t t 23

24 Tightly coupled visual-inertial SLAM (2 of 2) [RSS 2013] 24

25 Keyframe-Based Visual-Inertial SLAM Using Nonlinear Optimization [RSS 2013] S. Leutenegger, P. Furgale, V. Rabaud, M. Chli, K. Konolige, and R. Siegwart Robustness from tight coupling Also in difficult lighting conditions /motion blur Accuracy from non-linear optimization rather than filtering Combined reprojection error and IMU error cost function. Use of Keyframes to track changing dynamics: No drift in stand-still using marginalization of non-keyframe poses Real-time operation Fast keypoint matching using BRISKbased stereo processing Building reconstruction 25

26 Path planning for UAVs using RRBT [ICRA 2013] RRBT: Rapidly-exploring Random Belief Trees [Bry et al., ICRA 2011] Sample nominal poses to form candidate trajectories predicting future state distributions Plan the motion resulting to the smallest increase in uncertainty at the goal Can avoid obstacles and featureless regions (or degenerate configurations) Simulation: path planned is slightly longer than the direct path to excite necessary states and error covariance for better convergence origin destination Work with M. Achtelik 26

27 Uncertainty-aware UAV Path Planning Work with M. Achtelik 27

28 Uncertainty-aware UAV Path Planning b&w: original map and obtained path color: map following simulated featureless region & path Work with M. Achtelik 28

29 Conclusion Visual SLAM: has come a long way: from handheld to vision-stabilised flights of UAVs key to spatial awareness of robots bridges the gap between Computer Vision and Robotics Still work to be done before robots are ready for real missions Potential for great impact in search-and-rescue missions Main challenge: increase applicability & ease deployability Robustness to real environments and safety to users Fast camera dynamics (e.g. in aggressive maneuvers), dynamic scenes, sensor outage Path planning and obstacle avoidance Richer maps Semantic reasoning Multi-robot collaboration 29

30 Photo credits: Francois Pomerlaeu 30

SLAM II: SLAM for robotic vision-based perception

SLAM II: SLAM for robotic vision-based perception SLAM II: SLAM for robotic vision-based perception Margarita Chli Martin Rufli, Roland Siegwart Margarita Chli, Martin Rufli, Roland Siegwart SLAM II today s lecture Last time: how to do SLAM? Today: what

More information

SLAM II: SLAM for robotic vision-based perception

SLAM II: SLAM for robotic vision-based perception SLAM II: SLAM for robotic vision-based perception Margarita Chli Martin Rufli, Roland Siegwart Margarita Chli, Martin Rufli, Roland Siegwart SLAM II today s lecture Last time: how to do SLAM? Today: what

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

Autonomous Navigation for Flying Robots

Autonomous Navigation for Flying Robots Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 7.2: Visual Odometry Jürgen Sturm Technische Universität München Cascaded Control Robot Trajectory 0.1 Hz Visual

More information

Visual-Inertial Localization and Mapping for Robot Navigation

Visual-Inertial Localization and Mapping for Robot Navigation Visual-Inertial Localization and Mapping for Robot Navigation Dr. Guillermo Gallego Robotics & Perception Group University of Zurich Davide Scaramuzza University of Zurich - http://rpg.ifi.uzh.ch Mocular,

More information

Hybrids Mixed Approaches

Hybrids Mixed Approaches Hybrids Mixed Approaches Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline Why mixing? Parallel Tracking and Mapping Benefits

More information

Jakob Engel, Thomas Schöps, Daniel Cremers Technical University Munich. LSD-SLAM: Large-Scale Direct Monocular SLAM

Jakob Engel, Thomas Schöps, Daniel Cremers Technical University Munich. LSD-SLAM: Large-Scale Direct Monocular SLAM Computer Vision Group Technical University of Munich Jakob Engel LSD-SLAM: Large-Scale Direct Monocular SLAM Jakob Engel, Thomas Schöps, Daniel Cremers Technical University Munich Monocular Video Engel,

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

Augmented Reality, Advanced SLAM, Applications

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

More information

Real-Time Vision-Based State Estimation and (Dense) Mapping

Real-Time Vision-Based State Estimation and (Dense) Mapping Real-Time Vision-Based State Estimation and (Dense) Mapping Stefan Leutenegger IROS 2016 Workshop on State Estimation and Terrain Perception for All Terrain Mobile Robots The Perception-Action Cycle in

More information

Vol agile avec des micro-robots volants contrôlés par vision

Vol agile avec des micro-robots volants contrôlés par vision Vol agile avec des micro-robots volants contrôlés par vision From Active Perception to Event-based Vision Henri Rebecq from Prof. Davide Scaramuzza s lab GT UAV 17 Novembre 2016, Paris Davide Scaramuzza

More information

Semi-Dense Direct SLAM

Semi-Dense Direct SLAM Computer Vision Group Technical University of Munich Jakob Engel Jakob Engel, Daniel Cremers David Caruso, Thomas Schöps, Lukas von Stumberg, Vladyslav Usenko, Jörg Stückler, Jürgen Sturm Technical University

More information

Autonomous Navigation in Complex Indoor and Outdoor Environments with Micro Aerial Vehicles

Autonomous Navigation in Complex Indoor and Outdoor Environments with Micro Aerial Vehicles Autonomous Navigation in Complex Indoor and Outdoor Environments with Micro Aerial Vehicles Shaojie Shen Dept. of Electrical and Systems Engineering & GRASP Lab, University of Pennsylvania Committee: Daniel

More information

Dense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm

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

More information

Live Metric 3D Reconstruction on Mobile Phones ICCV 2013

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

More information

Visual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech

Visual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech Visual Odometry Features, Tracking, Essential Matrix, and RANSAC Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline The

More information

Autonomous navigation in industrial cluttered environments using embedded stereo-vision

Autonomous navigation in industrial cluttered environments using embedded stereo-vision Autonomous navigation in industrial cluttered environments using embedded stereo-vision Julien Marzat ONERA Palaiseau Aerial Robotics workshop, Paris, 8-9 March 2017 1 Copernic Lab (ONERA Palaiseau) Research

More information

Davide Scaramuzza. University of Zurich

Davide Scaramuzza. University of Zurich Davide Scaramuzza University of Zurich Robotics and Perception Group http://rpg.ifi.uzh.ch/ Scaramuzza, D., Fraundorfer, F., Visual Odometry: Part I - The First 30 Years and Fundamentals, IEEE Robotics

More information

Local features and image matching. Prof. Xin Yang HUST

Local features and image matching. Prof. Xin Yang HUST Local features and image matching Prof. Xin Yang HUST Last time RANSAC for robust geometric transformation estimation Translation, Affine, Homography Image warping Given a 2D transformation T and a source

More information

Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview

Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Arun Das 05/09/2017 Arun Das Waterloo Autonomous Vehicles Lab Introduction What s in a name? Arun Das Waterloo Autonomous

More information

FLaME: Fast Lightweight Mesh Estimation using Variational Smoothing on Delaunay Graphs

FLaME: Fast Lightweight Mesh Estimation using Variational Smoothing on Delaunay Graphs FLaME: Fast Lightweight Mesh Estimation using Variational Smoothing on Delaunay Graphs W. Nicholas Greene Robust Robotics Group, MIT CSAIL LPM Workshop IROS 2017 September 28, 2017 with Nicholas Roy 1

More information

Visual Navigation for Micro Air Vehicles

Visual Navigation for Micro Air Vehicles Visual Navigation for Micro Air Vehicles Abraham Bachrach, Albert S. Huang, Daniel Maturana, Peter Henry, Michael Krainin, Dieter Fox, and Nicholas Roy Computer Science and Artificial Intelligence Laboratory,

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

Monocular Visual-Inertial SLAM. Shaojie Shen Assistant Professor, HKUST Director, HKUST-DJI Joint Innovation Laboratory

Monocular Visual-Inertial SLAM. Shaojie Shen Assistant Professor, HKUST Director, HKUST-DJI Joint Innovation Laboratory Monocular Visual-Inertial SLAM Shaojie Shen Assistant Professor, HKUST Director, HKUST-DJI Joint Innovation Laboratory Why Monocular? Minimum structural requirements Widely available sensors Applications:

More information

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

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

More information

3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views - with Application to Fire-fighting Robots

3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views - with Application to Fire-fighting Robots 3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views - with Application to Fire-fighting Robots Yuncong Chen 1 and Will Warren 2 1 Department of Computer Science and Engineering,

More information

Monocular Visual Odometry

Monocular Visual Odometry Elective in Robotics coordinator: Prof. Giuseppe Oriolo Monocular Visual Odometry (slides prepared by Luca Ricci) Monocular vs. Stereo: eamples from Nature Predator Predators eyes face forward. The field

More information

Onboard Monocular Vision for Landing of an MAV on a Landing Site Specified by a Single Reference Image

Onboard Monocular Vision for Landing of an MAV on a Landing Site Specified by a Single Reference Image Onboard Monocular Vision for Landing of an MAV on a Landing Site Specified by a Single Reference Image Shaowu Yang, Sebastian A. Scherer, Konstantin Schauwecker and Andreas Zell Abstract This paper presents

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

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

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

More information

Computationally Efficient Visual-inertial Sensor Fusion for GPS-denied Navigation on a Small Quadrotor

Computationally Efficient Visual-inertial Sensor Fusion for GPS-denied Navigation on a Small Quadrotor Computationally Efficient Visual-inertial Sensor Fusion for GPS-denied Navigation on a Small Quadrotor Chang Liu & Stephen D. Prior Faculty of Engineering and the Environment, University of Southampton,

More information

Online Learning of Binary Feature Indexing for Real-time SLAM Relocalization

Online Learning of Binary Feature Indexing for Real-time SLAM Relocalization Online Learning of Binary Feature Indexing for Real-time SLAM Relocalization Youji Feng 1, Yihong Wu 1, Lixin Fan 2 1 Institute of Automation, Chinese Academy of Sciences 2 Nokia Research Center, Tampere

More information

Master Automática y Robótica. Técnicas Avanzadas de Vision: Visual Odometry. by Pascual Campoy Computer Vision Group

Master Automática y Robótica. Técnicas Avanzadas de Vision: Visual Odometry. by Pascual Campoy Computer Vision Group Master Automática y Robótica Técnicas Avanzadas de Vision: by Pascual Campoy Computer Vision Group www.vision4uav.eu Centro de Automá

More information

CSE 527: Introduction to Computer Vision

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

More information

Mobile Robots Summery. Autonomous Mobile Robots

Mobile Robots Summery. Autonomous Mobile Robots Mobile Robots Summery Roland Siegwart Mike Bosse, Marco Hutter, Martin Rufli, Davide Scaramuzza, (Margarita Chli, Paul Furgale) Mobile Robots Summery 1 Introduction probabilistic map-based localization

More information

Dense 3D Reconstruction from Autonomous Quadrocopters

Dense 3D Reconstruction from Autonomous Quadrocopters Dense 3D Reconstruction from Autonomous Quadrocopters Computer Science & Mathematics TU Munich Martin Oswald, Jakob Engel, Christian Kerl, Frank Steinbrücker, Jan Stühmer & Jürgen Sturm Autonomous Quadrocopters

More information

IEEE/CAA JOURNAL OF AUTOMATICA SINICA, VOL. 2, NO. 1, JANUARY Robust and Accurate Monocular Visual Navigation Combining IMU for a Quadrotor

IEEE/CAA JOURNAL OF AUTOMATICA SINICA, VOL. 2, NO. 1, JANUARY Robust and Accurate Monocular Visual Navigation Combining IMU for a Quadrotor IEEE/CAA JOURNAL OF AUTOMATICA SINICA, VOL. 2, NO. 1, JANUARY 2015 33 Robust and Accurate Monocular Visual Navigation Combining IMU for a Quadrotor Wei Zheng, Fan Zhou, and Zengfu Wang Abstract In this

More information

Citation for the original published paper (version of record):

Citation for the original published paper (version of record): http://www.diva-portal.org Preprint This is the submitted version of a paper published in Lecture Notes in Computer Science. Citation for the original published paper (version of record): Fan, Y., Aramrattana,

More information

3D Scene Reconstruction with a Mobile Camera

3D Scene Reconstruction with a Mobile Camera 3D Scene Reconstruction with a Mobile Camera 1 Introduction Robert Carrera and Rohan Khanna Stanford University: CS 231A Autonomous supernumerary arms, or "third arms", while still unconventional, hold

More information

Marker Based Localization of a Quadrotor. Akshat Agarwal & Siddharth Tanwar

Marker Based Localization of a Quadrotor. Akshat Agarwal & Siddharth Tanwar Marker Based Localization of a Quadrotor Akshat Agarwal & Siddharth Tanwar Objective Introduction Objective: To implement a high level control pipeline on a quadrotor which could autonomously take-off,

More information

Application questions. Theoretical questions

Application questions. Theoretical questions The oral exam will last 30 minutes and will consist of one application question followed by two theoretical questions. Please find below a non exhaustive list of possible application questions. The list

More information

Sensor Fusion: Potential, Challenges and Applications. Presented by KVH Industries and Geodetics, Inc. December 2016

Sensor Fusion: Potential, Challenges and Applications. Presented by KVH Industries and Geodetics, Inc. December 2016 Sensor Fusion: Potential, Challenges and Applications Presented by KVH Industries and Geodetics, Inc. December 2016 1 KVH Industries Overview Innovative technology company 600 employees worldwide Focused

More information

Lecture 13 Visual Inertial Fusion

Lecture 13 Visual Inertial Fusion Lecture 13 Visual Inertial Fusion Davide Scaramuzza Course Evaluation Please fill the evaluation form you received by email! Provide feedback on Exercises: good and bad Course: good and bad How to improve

More information

Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization

Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization Jung H. Oh, Gyuho Eoh, and Beom H. Lee Electrical and Computer Engineering, Seoul National University,

More information

Stable Vision-Aided Navigation for Large-Area Augmented Reality

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

More information

Long-term motion estimation from images

Long-term motion estimation from images Long-term motion estimation from images Dennis Strelow 1 and Sanjiv Singh 2 1 Google, Mountain View, CA, strelow@google.com 2 Carnegie Mellon University, Pittsburgh, PA, ssingh@cmu.edu Summary. Cameras

More information

Unmanned Aerial Vehicles

Unmanned Aerial Vehicles Unmanned Aerial Vehicles Embedded Control Edited by Rogelio Lozano WILEY Table of Contents Chapter 1. Aerodynamic Configurations and Dynamic Models 1 Pedro CASTILLO and Alejandro DZUL 1.1. Aerodynamic

More information

Autonomous Landing of MAVs on an Arbitrarily Textured Landing Site using Onboard Monocular Vision

Autonomous Landing of MAVs on an Arbitrarily Textured Landing Site using Onboard Monocular Vision Autonomous Landing of MAVs on an Arbitrarily Textured Landing Site using Onboard Monocular Vision Shaowu Yang, Sebastian A. Scherer, Konstantin Schauwecker and Andreas Zell Abstract This paper presents

More information

Collaborative Monocular SLAM with Multiple Micro Aerial Vehicles

Collaborative Monocular SLAM with Multiple Micro Aerial Vehicles 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) November 3-7, 2013. Tokyo, Japan Collaborative Monocular SLAM with Multiple Micro Aerial Vehicles Christian Forster 1, Simon

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

Real-time Dense Surface Reconstruction for Aerial Manipulation

Real-time Dense Surface Reconstruction for Aerial Manipulation Real-time Dense Surface Reconstruction for Aerial Manipulation Marco Karrer, Mina Kamel, Roland Siegwart and Margarita Chli Vision for Robotics Lab and Autonomous Abstract With robotic systems reaching

More information

Loosely Coupled Stereo Inertial Odometry on Low-cost System

Loosely Coupled Stereo Inertial Odometry on Low-cost System International Micro Air Vehicle Conference and Flight Competition (IMAV) 2017 143 Loosely Coupled Stereo Inertial Odometry on Low-cost System HaoChih, LIN, Francois, Defay Abstract We present a fast and

More information

Survey on Computer Vision for UAVs: Current Developments and Trends

Survey on Computer Vision for UAVs: Current Developments and Trends J Intell Robot Syst (2017) 87:141 168 DOI 10.1007/s10846-017-0483-z Survey on Computer Vision for UAVs: Current Developments and Trends Christoforos Kanellakis George Nikolakopoulos Received: 28 April

More information

MULTI-MODAL MAPPING. Robotics Day, 31 Mar Frank Mascarich, Shehryar Khattak, Tung Dang

MULTI-MODAL MAPPING. Robotics Day, 31 Mar Frank Mascarich, Shehryar Khattak, Tung Dang MULTI-MODAL MAPPING Robotics Day, 31 Mar 2017 Frank Mascarich, Shehryar Khattak, Tung Dang Application-Specific Sensors Cameras TOF Cameras PERCEPTION LiDAR IMU Localization Mapping Autonomy Robotic Perception

More information

Motion- and Uncertainty-aware Path Planning for Micro Aerial Vehicles *

Motion- and Uncertainty-aware Path Planning for Micro Aerial Vehicles * Motion- and Uncertainty-aware Path Planning for Micro Aerial Vehicles * Markus W. Achtelik and Simon Lynen Autonomous Systems Lab, ETH Zurich, CH-892 Zurich, Switzerland e-mail: markus.achtelik@mavt.ethz.ch,

More information

Visual Pose Estimation System for Autonomous Rendezvous of Spacecraft

Visual Pose Estimation System for Autonomous Rendezvous of Spacecraft Visual Pose Estimation System for Autonomous Rendezvous of Spacecraft Mark A. Post1, Junquan Li2, and Craig Clark2 Space Mechatronic Systems Technology Laboratory Dept. of Design, Manufacture & Engineering

More information

Autonomous 3D Reconstruction Using a MAV

Autonomous 3D Reconstruction Using a MAV Autonomous 3D Reconstruction Using a MAV Alexander Popov, Dimitrios Zermas and Nikolaos Papanikolopoulos Abstract An approach is proposed for high resolution 3D reconstruction of an object using a Micro

More information

Pose Estimation and Control of Micro-Air Vehicles

Pose Estimation and Control of Micro-Air Vehicles Pose Estimation and Control of Micro-Air Vehicles IVAN DRYANOVSKI, Ph.D. Candidate, Computer Science ROBERTO G. VALENTI, Ph.D. Candidate, Electrical Engineering Mentor: JIZHONG XIAO, Professor, Electrical

More information

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

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

More information

Large-Scale Robotic SLAM through Visual Mapping

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

More information

Collaborative 6DoF Relative Pose Estimation for two UAVs with Overlapping Fields of View

Collaborative 6DoF Relative Pose Estimation for two UAVs with Overlapping Fields of View Collaborative 6DoF Relative Pose Estimation for two UVs with Overlapping Fields of View Marco Karrer1, Mohit garwal1, Mina Kamel2, Roland Siegwart2 and Margarita Chli1 1 Vision for Robotics Lab and 2 utonomous

More information

A Loosely-Coupled Approach for Metric Scale Estimation in Monocular Vision-Inertial Systems

A Loosely-Coupled Approach for Metric Scale Estimation in Monocular Vision-Inertial Systems A Loosely-Coupled Approach for Metric Scale Estimation in Monocular Vision-Inertial Systems Ariane Spaenlehauer Vincent Frémont Y. Ahmet Şekercioğlu Isabelle Fantoni Abstract In monocular vision systems,

More information

Simultaneous Localization and Mapping (SLAM)

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

More information

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

Research Article Parallel Tracking and Mapping for Controlling VTOL Airframe

Research Article Parallel Tracking and Mapping for Controlling VTOL Airframe Journal of Control Science and Engineering Volume 2011, Article ID 413074, 10 pages doi:10.1155/2011/413074 Research Article Parallel Tracking and Mapping for Controlling VTOL Airframe Michal Jama 1 and

More information

Lecture: Autonomous micro aerial vehicles

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

More information

Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery

Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery 1 Charles TOTH, 1 Dorota BRZEZINSKA, USA 2 Allison KEALY, Australia, 3 Guenther RETSCHER,

More information

AUTONOMOUS NAVIGATION IN COMPLEX INDOOR AND OUTDOOR ENVIRONMENTS WITH MICRO AERIAL VEHICLES. Shaojie Shen A DISSERTATION

AUTONOMOUS NAVIGATION IN COMPLEX INDOOR AND OUTDOOR ENVIRONMENTS WITH MICRO AERIAL VEHICLES. Shaojie Shen A DISSERTATION AUTONOMOUS NAVIGATION IN COMPLEX INDOOR AND OUTDOOR ENVIRONMENTS WITH MICRO AERIAL VEHICLES Shaojie Shen A DISSERTATION in Electrical and Systems Engineering Presented to the Faculties of the University

More information

Introduction to Autonomous Mobile Robots

Introduction to Autonomous Mobile Robots Introduction to Autonomous Mobile Robots second edition Roland Siegwart, Illah R. Nourbakhsh, and Davide Scaramuzza The MIT Press Cambridge, Massachusetts London, England Contents Acknowledgments xiii

More information

COMBINING MEMS-BASED IMU DATA AND VISION-BASED TRAJECTORY ESTIMATION

COMBINING MEMS-BASED IMU DATA AND VISION-BASED TRAJECTORY ESTIMATION COMBINING MEMS-BASED IMU DATA AND VISION-BASED TRAJECTORY ESTIMATION F. Tsai a*, H. Chang b and A. Y. S. Su c a Center for Space and Remote Sensing Research b Department of Civil Engineering c Research

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

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

Intuitive 3D Maps for MAV Terrain Exploration and Obstacle Avoidance

Intuitive 3D Maps for MAV Terrain Exploration and Obstacle Avoidance J Intell Robot Syst (2011) 61:473 493 DOI 10.1007/s10846-010-9491-y Intuitive 3D Maps for MAV Terrain Exploration and Obstacle Avoidance Stephan Weiss Markus Achtelik Laurent Kneip Davide Scaramuzza Roland

More information

A Reactive Bearing Angle Only Obstacle Avoidance Technique for Unmanned Ground Vehicles

A Reactive Bearing Angle Only Obstacle Avoidance Technique for Unmanned Ground Vehicles Proceedings of the International Conference of Control, Dynamic Systems, and Robotics Ottawa, Ontario, Canada, May 15-16 2014 Paper No. 54 A Reactive Bearing Angle Only Obstacle Avoidance Technique for

More information

Short-term UAV Path-Planning with Monocular-Inertial SLAM in the Loop

Short-term UAV Path-Planning with Monocular-Inertial SLAM in the Loop Short-term UAV Path-Planning with Monocular-Inertial SLAM in the Loop Ignacio Alzugaray, Lucas Teixeira and Margarita Chli Vision for Robotics Lab, ETH Zurich, Switzerland Abstract Small Unmanned Aerial

More information

Motion Planning for an Autonomous Helicopter in a GPS-denied Environment

Motion Planning for an Autonomous Helicopter in a GPS-denied Environment Motion Planning for an Autonomous Helicopter in a GPS-denied Environment Svetlana Potyagaylo Faculty of Aerospace Engineering svetapot@tx.technion.ac.il Omri Rand Faculty of Aerospace Engineering omri@aerodyne.technion.ac.il

More information

A Fuzzy Brute Force Matching Method for Binary Image Features

A Fuzzy Brute Force Matching Method for Binary Image Features A Fuzzy Brute Force Matching Method for Binary Image Features Erkan Bostanci 1, Nadia Kanwal 2 Betul Bostanci 3 and Mehmet Serdar Guzel 1 1 (Computer Engineering Department, Ankara University, Turkey {ebostanci,

More information

Visual-Inertial RGB-D SLAM for Mobile Augmented Reality

Visual-Inertial RGB-D SLAM for Mobile Augmented Reality Visual-Inertial RGB-D SLAM for Mobile Augmented Reality Williem 1, Andre Ivan 1, Hochang Seok 2, Jongwoo Lim 2, Kuk-Jin Yoon 3, Ikhwan Cho 4, and In Kyu Park 1 1 Department of Information and Communication

More information

15 Years of Visual SLAM

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

More information

ROBOT TEAMS CH 12. Experiments with Cooperative Aerial-Ground Robots

ROBOT TEAMS CH 12. Experiments with Cooperative Aerial-Ground Robots ROBOT TEAMS CH 12 Experiments with Cooperative Aerial-Ground Robots Gaurav S. Sukhatme, James F. Montgomery, and Richard T. Vaughan Speaker: Jeff Barnett Paper Focus Heterogeneous Teams for Surveillance

More information

Simultaneous Localization

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

More information

Scanning and Printing Objects in 3D Jürgen Sturm

Scanning and Printing Objects in 3D Jürgen Sturm Scanning and Printing Objects in 3D Jürgen Sturm Metaio (formerly Technical University of Munich) My Research Areas Visual navigation for mobile robots RoboCup Kinematic Learning Articulated Objects Quadrocopters

More information

Onboard IMU and Monocular Vision Based Control for MAVs in Unknown In- and Outdoor Environments

Onboard IMU and Monocular Vision Based Control for MAVs in Unknown In- and Outdoor Environments Research Collection Conference Paper Onboard IMU and Monocular Vision Based Control for MAVs in Unknown In- and Outdoor Environments Author(s): Achtelik, Markus W.; Achtelik, Michael; Weiss, Stephan; Siegwart,

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

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

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

Egomotion Estimation by Point-Cloud Back-Mapping

Egomotion Estimation by Point-Cloud Back-Mapping Egomotion Estimation by Point-Cloud Back-Mapping Haokun Geng, Radu Nicolescu, and Reinhard Klette Department of Computer Science, University of Auckland, New Zealand hgen001@aucklanduni.ac.nz Abstract.

More information

Optimal surveillance coverage for teams of micro aerial vehicles in GPS-Denied environments using onboard vision

Optimal surveillance coverage for teams of micro aerial vehicles in GPS-Denied environments using onboard vision Zurich Open Repository and Archive University of Zurich Main Library Strickhofstrasse 39 CH-8057 Zurich www.zora.uzh.ch Year: 2012 Optimal surveillance coverage for teams of micro aerial vehicles in GPS-Denied

More information

3-Point RANSAC for Fast Vision based Rotation Estimation using GPU Technology

3-Point RANSAC for Fast Vision based Rotation Estimation using GPU Technology 3-Point RANSAC for Fast Vision based Rotation Estimation using GPU Technology Danial Kamran 1, Mohammad T. Manzuri 1, Ali Marjovi 2 and Mahdi Karimian 1 Abstract In many sensor fusion algorithms, the vision

More information

ORB SLAM 2 : an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras

ORB SLAM 2 : an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras ORB SLAM 2 : an OpenSource SLAM System for Monocular, Stereo and RGBD Cameras Raul urartal and Juan D. Tardos Presented by: Xiaoyu Zhou Bolun Zhang Akshaya Purohit Lenord Melvix 1 Outline Background Introduction

More information

Emerging Vision Technologies: Enabling a New Era of Intelligent Devices

Emerging Vision Technologies: Enabling a New Era of Intelligent Devices Emerging Vision Technologies: Enabling a New Era of Intelligent Devices Computer vision overview Computer vision is being integrated in our daily lives Acquiring, processing, and understanding visual data

More information

A Constant-Time Efficient Stereo SLAM System

A Constant-Time Efficient Stereo SLAM System A Constant-Time Efficient Stereo SLAM System Christopher Mei, Gabe Sibley, Mark Cummins, Ian Reid and Paul Newman Department of Engineering Science University of Oxford, OX1 3PJ, Oxford, UK {cmei,gsibley,mjc,ian,pnewman}@robots.ox.ac.uk

More information

GOMSF: Graph-Optimization based Multi-Sensor Fusion for robust UAV pose estimation

GOMSF: Graph-Optimization based Multi-Sensor Fusion for robust UAV pose estimation GOMSF: Graph-Optimization based Multi-Sensor Fusion for robust UAV pose estimation Ruben Mascaro1, Lucas Teixeira1, Timo Hinzmann, Roland Siegwart and Margarita Chli1 1 Vision for Robotics Lab, ETH Zurich,

More information

Monocular Visual-Inertial State Estimation for Micro Aerial Vehicles

Monocular Visual-Inertial State Estimation for Micro Aerial Vehicles MATEC Web of Conferences 139, 68 (17 ICMITE 17 DOI: 1.151/matecconf/1713968 Monocular Visual-Inertial State Estimation for Micro Aerial Vehicles Yao Xiao 1,, Xiaogang Ruan 1, Xiaoping Zhang 1, and Pengfei

More information

COS Lecture 13 Autonomous Robot Navigation

COS Lecture 13 Autonomous Robot Navigation COS 495 - Lecture 13 Autonomous Robot Navigation Instructor: Chris Clark Semester: Fall 2011 1 Figures courtesy of Siegwart & Nourbakhsh Control Structure Prior Knowledge Operator Commands Localization

More information

Improved line tracker using IMU and Vision for visual servoing

Improved line tracker using IMU and Vision for visual servoing Proceedings of Australasian Conference on Robotics and Automation, - Dec 3, University of New South Wales, Sydney Australia Improved line tracker using IMU and Vision for visual servoing Inkyu Sa and Peter

More information

Offloading UAV Navigation Computation to the Cloud Sriramya Ramya Bhamidipati and Grace Xingxin Gao

Offloading UAV Navigation Computation to the Cloud Sriramya Ramya Bhamidipati and Grace Xingxin Gao Offloading UAV Navigation Computation to the Cloud Sriramya Ramya Bhamidipati and Grace Xingxin Gao SCPNT 2016 November 01 2016 UAV Navigation in Urban Areas Challenges Limited battery life Restricted

More information

Guidance: A Visual Sensing Platform For Robotic Applications

Guidance: A Visual Sensing Platform For Robotic Applications Guidance: A Visual Sensing Platform For Robotic Applications Guyue Zhou, Lu Fang, Ketan Tang, Honghui Zhang, Kai Wang, Kang Yang {guyue.zhou, ketan.tang, honghui.zhang, kevin.wang, kang.yang}@dji.com,

More information

Visual SLAM. An Overview. L. Freda. ALCOR Lab DIAG University of Rome La Sapienza. May 3, 2016

Visual SLAM. An Overview. L. Freda. ALCOR Lab DIAG University of Rome La Sapienza. May 3, 2016 An Overview L. Freda ALCOR Lab DIAG University of Rome La Sapienza May 3, 2016 L. Freda (University of Rome La Sapienza ) Visual SLAM May 3, 2016 1 / 39 Outline 1 Introduction What is SLAM Motivations

More information

Anibal Ollero Professor and head of GRVC University of Seville (Spain)

Anibal Ollero Professor and head of GRVC University of Seville (Spain) Aerial Manipulation Anibal Ollero Professor and head of GRVC University of Seville (Spain) aollero@us.es Scientific Advisor of the Center for Advanced Aerospace Technologies (Seville, Spain) aollero@catec.aero

More information