Particle Filters for Location Estimation in Ubiquitous Computing: A Case Study Jeffrey Hightower and Gaetano Borriello Intel Research and University of.

Slides:



Advertisements
Similar presentations
State Estimation and Kalman Filtering CS B659 Spring 2013 Kris Hauser.
Advertisements

Dependence Precedence. Precedence & Dependence Can we execute a 1000 line program with 1000 processors in one step? What are the issues to deal with in.
Sonar and Localization LMICSE Workshop June , 2005 Alma College.
My first aperosentation 9/6/2008 Marios Karagiannis.
Location and Tracking Spring 2004: Location Recognition Larry Rudolph Location of what? Services applications, resources, sensors, actuators where.
Probabilistic Robotics
Happy Home Helper Jeremy Searle Apr 28, 2004 A Learning Home Automation System.
A SYSTEM FOR AUTONOMOUS TRACKING AND FOLLOWING OF SHARKS WITH AN AUTONOMOUS UNDERWATER VEHICLE Esfandiar Manii Advisor: Dr. Christopher M. Clark A Presentation.
Accuracy Characterization for Metropolitan-scale Wi-Fi Localization Yu-Chung Cheng (UCSD, Intel Research) Yatin Chawathe (Intel Research) Anthony LaMarca.
ACCURACY CHARACTERIZATION FOR METROPOLITAN-SCALE WI-FI LOCALIZATION Presented by Jack Li March 5, 2009.
Accuracy Characterization for Metropolitan-scale Wi-Fi Localization Ying Wang, Xia Li Ying Wang, Xia Li.
Introduction to Robotics In the name of Allah. Introduction to Robotics o Leila Sharif o o Lecture #2: The Big.
Project Progress Presentation Coffee delivery mission Dec, 10, 2007 NSH 3211 Hyun Soo Park, Iacopo Gentilini 1.
1 Indoor Location Sensing Using Active RFID Lionel M. Ni, HKUST Yunhao Liu, HKUST Yiu Cho Lau, IBM Abhishek P. Patil, MSU Indoor Location Sensing Using.
1 ENHANCED RSSI-BASED HIGH ACCURACY REAL-TIME USER LOCATION TRACKING SYSTEM FOR INDOOR AND OUTDOOR ENVIRONMENTS Department of Computer Science and Information.
Location Systems for Ubiquitous Computing Jeffrey Hightower and Gaetano Borriello.
What is Assisted Cognition? Henry Kautz University of Washington Computer Science & Engineering.
Bayesian Filtering for Location Estimation D. Fox, J. Hightower, L. Liao, D. Schulz, and G. Borriello Presented by: Honggang Zhang.
UNIVERSITY of CRETE Fall04 – HY436: Mobile Computing and Wireless Networks Location Sensing Overview Lecture 8 Maria Papadopouli
Review: Accuracy Characterization for Metropolitan-scale Wi-Fi Localization Authors: Cheng, Chawathe, LaMacra, Krumm 2005 Slides Adapted from Cheng, MobiSys.
Location-sensing using the IEEE Infrastructure and the Peer-to-peer Paradigm for mobile computing applications Anastasia Katranidou Supervisor:
Particle Filtering. Sensors and Uncertainty Real world sensors are noisy and suffer from missing data (e.g., occlusions, GPS blackouts) Use sensor models.
RFID and Positioning. Outline RFID Introduction Indoor Localization RFID positioning Algorithm – LANDMARC – RFID-Based 3-D Positioning Schemes RFID application.
CS 4730 Physical Simulation CS 4730 – Computer Game Design.
Innovative RFID Localization System Bassel Tawfik.
Smart Environments for Occupancy Sensing and Services Paper by Pirttikangas, Tobe, and Thepvilojanapong Presented by Alan Kelly December 7, 2011.
Patrick Lazar, Tausif Shaikh, Johanna Thomas, Kaleel Mahmood
Presented by: Chaitanya K. Sambhara Paper by: Maarten Ditzel, Caspar Lageweg, Johan Janssen, Arne Theil TNO Defence, Security and Safety, The Hague, The.
Indoor Localization Carick Wienke Advisor: Dr. Nicholas Kirsch University of New Hampshire ECE 791H Using a Modern Smartphone.
1 CSCE 5013: Hot Topics in Mobile and Pervasive Computing Nilanjan Banerjee Hot Topic in Mobile and Pervasive Computing University of Arkansas Fayetteville,
Particle Filter & Search
Robotics- Basic On/Off Control Considerations. On/Off Control Forms the basis of most robotics operations Is deceptively simple until the consequences.
Multiple Autonomous Ground/Air Robot Coordination Exploration of AI techniques for implementing incremental learning. Development of a robot controller.
Beyond One-dollar Mouse: A Battery-free Device for 3D Human-Computer Interaction via RFID Tags Qiongzheng Lin Lei Yang,Yuxin Sun,Tianci Liu,Xiang-Yang.
Guided Notes on Gathering Weather Data
Mapping and Localization with RFID Technology Matthai Philipose, Kenneth P Fishkin, Dieter Fox, Dirk Hahnel, Wolfram Burgard Presenter: Aniket Shah.
Robotics Intensive: Day 4 Gui Cavalcanti 1/17/2012.
Dynamic Fine-Grained Localization in Ad-Hoc Networks of Sensors Weikuan Yu Dept. of Computer and Info. Sci. The Ohio State University.
Young Ki Baik, Computer Vision Lab.
National Taiwan University Graduate Institute of Electronics Engineering National Taiwan University Graduate Institute of Electronics Engineering A CCESS.
Stereo Object Detection and Tracking Using Clustering and Bayesian Filtering Texas Tech University 2011 NSF Research Experiences for Undergraduates Site.
FOREWORD By: Howard Shrobe MIT CS & AI Laboratory
Robotics Sharif In the name of Allah. Robotics Sharif Introduction to Robotics o Leila Sharif o o Lecture #2: The.
Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 5.1: State Estimation Jürgen Sturm Technische Universität München.
Automated Intruder Tracking using Particle Filtering and a Network of Binary Motion Sensors Jeremy Schiff EECS Department University of California, Berkeley.
–thermometer –barometer –anemometer –hygrometer Objectives Recognize the importance of accurate weather data. Describe the technology used to collect.
GPS Provider:  GPS signal Network Location Provider:  Cell ID  Wi-Fi.
CV Workshop: Multiple Target Tracking Michael Rubinstein IDC Jan
Training Conditional Random Fields using Virtual Evidence Boosting Lin Liao, Tanzeem Choudhury †, Dieter Fox, and Henry Kautz University of Washington.
Android - Location Based Services. Google Play services facilitates adding location awareness to your app with automated location tracking Geo fencing.
Outline Location sensing techniques Location systems properties Existing systems overview WiFi localization techniques WPI precision personnel locator.
Mobile and Pervasive Computing - 4 Location in Pervasive Computing Presented by: Dr. Adeel Akram University of Engineering and Technology, Taxila,Pakistan.
CS101 Parts of a Computer. What we know! To be a computer it needs to do four things: –1 –2 –3 –4 We might already know a lot about three of these requirements.
Particle Filtering. Sensors and Uncertainty Real world sensors are noisy and suffer from missing data (e.g., occlusions, GPS blackouts) Use sensor models.
Robots.
Location System for Ubiquitous Computing Jeffrey Hightower Gaetano Borriello University of Washington.
Cooperative Location-Sensing for Wireless Networks Charalampos Fretzagias and Maria Papadopouli Department of Computer Science University of North Carolina.
Planning Strategies RSS II Lecture 6 September 21, 2005.
1 VeTrack: Real Time Vehicle Tracking in Uninstrumented Indoor Environments Mingmin Zhao 1, Tao Ye 1, Ruipeng Gao 1, Fan Ye 2, Yizhou Wang 1, Guojie Luo.
University of Pennsylvania 1 GRASP Control of Multiple Autonomous Robot Systems Vijay Kumar Camillo Taylor Aveek Das Guilherme Pereira John Spletzer GRASP.
Microsoft Kinect How does a machine infer body position?
Mobile and Pervasive Computing - 4 Location in Pervasive Computing
Understanding and using Location technologies
Location Sensing (Inference)
Probabilistic Reasoning Over Time
CS101 Parts of a Computer.
Particle filters for Robot Localization
Indoor Location Estimation Using Multiple Wireless Technologies
A schematic overview of localization in wireless sensor networks
Overview: Chapter 2 Localization and Tracking
Presentation transcript:

Particle Filters for Location Estimation in Ubiquitous Computing: A Case Study Jeffrey Hightower and Gaetano Borriello Intel Research and University of Washingon, CS and Eng.

The point Location is a big part of context Ubiquitous computers need to guess location without direct input Several different types sensors for one application is more effective in guessing location

Current Technology Sensing technologies: GPS, infrared, ultrasound, WiFi, vision, etc… Each has its own strengths and weaknesses Most systems designed to a specific type of sensor, rigid algorithms

Particle Filters “Probabilistic approximations” to track location of robots Not modeled on any one type of sensor Combines data from various objects in the environment Machine learning capabilities increase accuracy but diminish generality

Experiment Procedure Building equipped with a combination of infrared, ultrasound, and WiFi tracking systems “Ground truth” collected by highly accurate robot traveling through the building making human-like motions while wearing badges, RFID tags and other devices Tracked for 15 minutes ultrasound and 537 infrafed measurements

Experiment Results Compared accuracy of deterministic position algorithms (Point, Centroid, Smooth Centroid, Smooth Weighted Centroid) with particle filters Particle filter as accurate as any other algorithm, much more accurate when different sensors were combined

What Does This Mean? Using multiple location-sensing technologies produces more accurate results because they each have different strengths/capabilities Particle filters designed to be non- specific, so they’re a good choice of algorithm

Tradeoffs Particle filters require more computation time and memory…but many devices can handle it and processor speeds keep going up Accuracy greatly increases with repetition…but might take a while to learn

Implications Seamless location-sensing between outdoor and indoor environments Applications/devices unaware of the sensing technologies they depend upon Potential ability to infer human activity, situational context other than location

Discussion Do we really want to be weighed down with all these badges, or are we going to wait until the sensing technologies are combined? Why does a device need to know where we are? What are the advantages? What if it’s wrong? Do we want our computers to stalk us? How do we turn it off? Minority Report -- cut out our eyes…