Robust Activity Recognition Henry Kautz University of Washington Computer Science & Engineering graduate students: Don Patterson, Lin Liao, Krzysztof Gajos,

Slides:



Advertisements
Similar presentations
Opportunity Knocks: A Community Navigation Aid Henry Kautz Don Patterson Dieter Fox Lin Liao University of Washington Computer Science & Engineering.
Advertisements

Recognizing Human Activity from Sensor Data Henry Kautz University of Washington Computer Science & Engineering graduate students: Don Patterson, Lin Liao.
State Estimation and Kalman Filtering CS B659 Spring 2013 Kris Hauser.
Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.
1 Assisted Cognition Henry Kautz Don Patterson, Nan LI Oren Etzioni, Dieter Fox University of Washington Department of Computer Science & Engineering.
Dynamic Bayesian Networks (DBNs)
CSE 5522: Survey of Artificial Intelligence II: Advanced Techniques Instructor: Alan Ritter TA: Fan Yang.
Assisted Cognition Henry Kautz University of Rochester Computer Science.
The Future of Computing CSC 161: The Art of Programming Prof. Henry Kautz 12/2/
Location and Tracking Spring 2004: Location Recognition Larry Rudolph Location of what? Services applications, resources, sensors, actuators where.
Hidden Markov Models Reading: Russell and Norvig, Chapter 15, Sections
1 Assisted Cognition Henry Kautz, Oren Etzioni, & Dieter Fox University of Washington Department of Computer Science & Engineering.
Integrating Bayesian Networks and Simpson’s Paradox in Data Mining Alex Freitas University of Kent Ken McGarry University of Sunderland.
Dieter Fox University of Washington Department of Computer Science & Engineering.
Civil and Environmental Engineering Carnegie Mellon University Sensors & Knowledge Discovery (a.k.a. Data Mining) H. Scott Matthews April 14, 2003.
Autonomous Robot Navigation Panos Trahanias ΗΥ475 Fall 2007.
1 Assisted Cognition Henry Kautz, Oren Etzioni, Dieter Fox, Gaetano Borriello, Larry Arnstein University of Washington Department of Computer Science &
Part 2 of 3: Bayesian Network and Dynamic Bayesian Network.
What is Assisted Cognition? Henry Kautz University of Washington Computer Science & Engineering.
Probabilistic Databases Amol Deshpande, University of Maryland.
CS 188: Artificial Intelligence Fall 2009 Lecture 19: Hidden Markov Models 11/3/2009 Dan Klein – UC Berkeley.
The New Age of Commonsense Reasoning Henry Kautz University of Rochester.
CSE 515 Statistical Methods in Computer Science Instructor: Pedro Domingos.
CS Machine Learning. What is Machine Learning? Adapt to / learn from data  To optimize a performance function Can be used to:  Extract knowledge.
Personalized Medicine Research at the University of Rochester Henry Kautz Department of Computer Science.
Bayesian Filtering for Robot Localization
Sensys 2009 Speaker:Lawrence.  Introduction  Overview & Challenges  Algorithm  Travel Time Estimation  Evaluation  Conclusion.
Ambulation : a tool for monitoring mobility over time using mobile phones Computational Science and Engineering, CSE '09. International Conference.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Chapter 8 Prediction Algorithms for Smart Environments
Using Neural Networks in Database Mining Tino Jimenez CS157B MW 9-10:15 February 19, 2009.
From Bayesian Filtering to Particle Filters Dieter Fox University of Washington Joint work with W. Burgard, F. Dellaert, C. Kwok, S. Thrun.
Making Sense of Sensors Henry Kautz Department of Computer Science & Engineering University of Washington, Seattle, WA Funding for this research is provided.
Bayesian networks Classification, segmentation, time series prediction and more. Website: Twitter:
The Assisted Cognition Project Henry Kautz, Dieter Fox, Gaetano Boriello Lin Liao, Brian Ferris, Evan Welborne (UW CSE) Don Patterson (UW / UC Irvine)
Mapping and Localization with RFID Technology Matthai Philipose, Kenneth P Fishkin, Dieter Fox, Dirk Hahnel, Wolfram Burgard Presenter: Aniket Shah.
Inferring High-Level Behavior from Low-Level Sensors Don Peterson, Lin Liao, Dieter Fox, Henry Kautz Published in UBICOMP 2003 ICS 280.
Recognizing Activities of Daily Living from Sensor Data Henry Kautz Department of Computer Science University of Rochester.
1 Robot Environment Interaction Environment perception provides information about the environment’s state, and it tends to increase the robot’s knowledge.
January Smart Environments: Artificial Intelligence in the Home and Beyond Diane J. Cook
Introduction to the 2007 Workshop on Intelligent Systems for Assisted Cognition Henry Kautz University of Rochester Department of Computer Science.
의미 모델링 Elaborating Sensor Data using Temporal and Spatial Commonsense Reasoning + Mining Models of Human Activities from the Web 지능 기반 시스템 응용
Learning and Inferring Transportation Routines By: Lin Liao, Dieter Fox and Henry Kautz Best Paper award AAAI’04.
The New Age of Commonsense Reasoning Henry Kautz University of Rochester.
Training Conditional Random Fields using Virtual Evidence Boosting Lin Liao, Tanzeem Choudhury †, Dieter Fox, and Henry Kautz University of Washington.
Inferring High-Level Behavior from Low-Level Sensors Donald J. Patterson, Lin Liao, Dieter Fox, and Henry Kautz.
Data Mining and Decision Support
OBJECT TRACKING USING PARTICLE FILTERS. Table of Contents Tracking Tracking Tracking as a probabilistic inference problem Tracking as a probabilistic.
Project ACCESS Henry Kautz, Dieter Fox, Gaetano Boriello (UW CSE) Don Patterson (UW / UC Irvine) Kurt Johnson, Pat Brown, Mark Harniss (UW Rehabilitation.
REU 2007 Computer Science and Engineering Department The University of Texas at Arlington Research Experiences for Undergraduates in Information Processing.
Pervasive Computing MIT SMA 5508 Spring 2006 Larry Rudolph 1 Tracking Indoors.
Sensor Analysis – Part II A literature based exploration Thomas Plötz [material taken from the original papers and John Krumm “Ubiquitous Computing Fundamentals”
1 Relational Factor Graphs Lin Liao Joint work with Dieter Fox.
Thrust IIA: Environmental State Estimation and Mapping Dieter Fox (Lead) Nicholas Roy MURI 8 Kickoff Meeting 2007.
10-1 Probabilistic Robotics: FastSLAM Slide credits: Wolfram Burgard, Dieter Fox, Cyrill Stachniss, Giorgio Grisetti, Maren Bennewitz, Christian Plagemann,
Learning and Inferring Transportation Routines Lin Liao, Don Patterson, Dieter Fox, Henry Kautz Department of Computer Science and Engineering University.
Ubiquitous means ‘everywhere’
Instructor: Eyal Amir Grad TAs: Wen Pu, Yonatan Bisk Undergrad TAs: Sam Johnson, Nikhil Johri CS 440 / ECE 448 Introduction to Artificial Intelligence.
Assisted Cognition Systems Henry Kautz Department of Computer Science.
Understanding Human Behavior from Sensor Data
Understanding Human Behavior from Sensor Data
Understanding Human Behavior from Sensor Data
Contextual Intelligence as a Driver of Services Innovation
Thrust IC: Action Selection in Joint-Human-Robot Teams
Markov Chain Monte Carlo
CSCI 5822 Probabilistic Models of Human and Machine Learning
Overview of Machine Learning
Probability and Time: Markov Models
Discovering Activities of Daily Life Using RFID’s
Finding Periodic Discrete Events in Noisy Streams
Presentation transcript:

Robust Activity Recognition Henry Kautz University of Washington Computer Science & Engineering graduate students: Don Patterson, Lin Liao, Krzysztof Gajos, Karthik Gopalratnam CSE faculty: Dieter Fox, Gaetano Borriello UW School of Medicine: Kurt Johnson, Pat Brown, Brian Dudgeon, Mark Harniss Intel Research: Matthai Philipose, Mike Perkowitz, Ken Fishkin, Tanzeem Choudhury

In the Not Too Distant Future... Pervasive sensing infrastructure GPS enabled phones RFID tags on all consumer products Electronic diaries (MS SenseCam) Healthcare crisis Aging baby boomers – epidemic of Alzheimer’s Disease Deinstitutionalization of the cognitively disabled Nationwide shortage of caretaking professionals

...An Opportunity Develop technology to Support independent living by people with cognitive disabilities At home At work Throughout the community Improve health care Long term monitoring of activities of daily living (ADL’s) Intervention before a health crisis

The UW Assisted Cognition Project Synthesis of work in Ubiquitous computing Artificial intelligence Human-computer interaction ACCESS Support use of public transit UW CSE & Rehabilitation Medicine CARE ADL monitoring and assistance UW CSE & Intel Research

This Talk Building models of everyday plans and goals From sensor data By mining textual description By engineering commonsense knowledge Tracking and predicting a user’s behavior Noisy and incomplete sensor data Recognizing user errors First steps

ACCESS Assisted Cognition in Community, Employment, & Support Settings Supported by the National Institute on Disability & Rehabilitation Research (NIDDR) Learning & Reasoning About Transportation Routines

Task Given a data stream from a wearable GPS unit... Infer the user’s location and mode of transportation (foot, car, bus, bike,...) Predict where user will go Detect novel behavior User errors? Opportunities for learning?

Why Inference Is Not Trivial People don’t have wheels Systematic GPS error We are not in the woods Dead and semi-dead zones Lots of multi-path propagation Inside of vehicles Inside of buildings Not just location tracking Mode, Prediction, Novelty

GPS Receivers We Used Nokia 6600 Java Cell Phone with Bluetooth GPS unit GeoStats wearable GPS logger

Geographic Information Systems Bus routes and bus stops Data source: Metro GIS Street map Data source: Census 2000 Tiger/line data

Architecture Learning Engine Inference Engine GIS Database Goals Paths Modes Errors

Probabilistic Reasoning Graphical model: Dynamic Bayesian network Inference engine: Rao-Blackwellised particle filters Learning engine: Expectation-Maximization (EM) algorithm

Flat Model: State Space Transportation Mode Velocity Location Block Position along block At bus stop, parking lot,...? GPS Offset Error GPS signal

Motion Model for Mode of Transportation

Rao-Blackwellised Particle Filtering Inference: estimate current state distribution given all past readings Particle filtering Evolve approximation to state distribution using samples (particles) Supports multi-modal distributions Supports discrete variables (e.g.: mode) Rao-Blackwellisation Particles include distributions over variables, not just single samples Improved accuracy with fewer particles

Tracking blue = foot, green = bus, red = car

Learning User model = DBN parameters Transitions between blocks Transitions between modes Learning: Monte-Carlo EM Unlabeled data 30 days of one user, logged at 2 second intervals (when outdoors) 3-fold cross validation

Results Model Mode Prediction Accuracy Decision Tree (supervised) 55% Prior w/o bus info60% Prior with bus info78% Learned84%

Probability of correctly predicting the future City Blocks Prediction Accuracy How can we improve predictive power?

Transportation Routines BA Goals work, home, friends, restaurant, doctor’s,... Trip segments Home to Bus stop A on Foot Bus stop A to Bus stop B on Bus Bus stop B to workplace on Foot Work

Hierarchical Model x k-1 z k-1 zkzk xkxk m k-1 mkmk Transportation mode x= GPS reading t k-1 tktk g k-1 gkgk Goal Trip segment

Hierarchical Learning Learn flat model Infer goals Locations where user is often motionless Infer trip segment begin / end points Locations with high mode transition probability Infer trips segments High-probability single-mode block transition sequences between segment begin / end points Perform hierarchical EM learning

Inferring Goals

Inferring Trip Segments Going to workGoing home

Correct goal and route predicted 100 blocks away

Application: Opportunity Knocks Demonstrated at AAHA Future of Aging Services, Washington, DC, March, 2004

Novelty Detection Approach: model-selection Run two trackers in parallel Tracker 1: learned hierarchical model Tracker 2: untrained flat model Estimate the likelihood of each tracker given the observations

Missing the bus stop

Novelty Detection

CARE Cognitive Assistance in Real-world Environments supported by the Intel Research Council Learning & Inferring Activities of Daily Living

Research Hypothesis Observation: activities of daily living involve the manipulation of many physical objects Cooking, cleaning, eating, personal hygiene, exercise, hobbies,... Hypothesis: can recognize activities from a time-sequence of object “touches” Such models are robust and easily learned or engineered

Sensing Object Manipulation RFID: Radio- frequency ID tags Small Semi-passive Durable Cheap

Where Can We Put Tags?

How Can We Sense Them? coming... wall-mounted “sparkle reader”

Example Data Stream

Technical Approach Define (or learn) activities in simple, high-level language Multi-step, partially-ordered activities Varying durations Probabilistic association between activities and objects Compile to a DBN Infer behavior using particle filtering

Making Tea

Activity Library

Building Models Core ADL’s amenable to classic knowledge engineering Open-ended, fine-grained models: infer from natural language texts? Perkowitz et al., “Mining Models of Human Activities from the Web”, WWW-2004

Translation to DBN Tricky issues: Time Partial orders Object-use probabilities 80% chance of using the teapot sometime during the “heat water” step Instantaneous probability of seeing teapot is not fixed! Consider: 100% chance of using teapot if making tea

DBN Encoding: Duration DtDt AtAt A t+1 D t+1

DBN Encoding: Partial Orders PtPt AtAt A t+1 PtPt

DBN Encoding: Object Probabilities ztzt DtDt AtAt OtOt HtHt Instantaneous probability of touching an object cannot be a constant

DBN Encoding ztzt PtPt DtDt AtAt OtOt HtHt A t+1 D t+1 H t+1 PtPt

What’s in a Particle? Sample of Activity Starting time – sufficient to represent distribution of Duration History list of objects Partial-order “credits”

Experimental Setup Hand-built library of 14 ADL’s 17 test subjects Each asked to perform 12 of the ADL’s Data not segmented No training on individual test subjects

Sample Output

Results ADLPrecisionRecall 1Grooming92 2Tooth brushing7078 3Toileting73 4Dishwashing Housecleaning Appliance use8478 7Adjust furnace Laundry Prepare snack Prepare beverage64 11Use telephone Leisure activities Infant care Take medication10082 Overall8873

Key Next Steps Parameter learning Timing Object probabilities Structure learning New activities from sensor data Efficient inference for Interrupted activities Abandoned activities Malformed activities Relational models Hierarchical classes of objects Hierarchical classes of activities

Ultimately... Affective state agitated, calm, attentive,... Physiological states hungry, tired, dizzy,... Interactions between people T. Choudhury – Social dynamics Principled human-computer interaction Decision-theoretic control of interventions

Why Now? A goal of much work of AI in the 1970’s was to create programs that could understand the narrative of ordinary human experience This area pretty much disappeared Missing probabilistic tools Systems not able to experience world Lacked focus – “understand” to what end? Today: the tools, the sensors, motivation

That Other Talk... Combining Component Caching and Clause Learning for Effective Model Counting Beame, Bacchus, Kautz, Pitassi, & Sang (SAT 2004, Vancouver BC) Unifies algorithms for SAT and Bayesian inference DPLL-based, generalizes recursive conditioning Exact inference in large, non-tree-like networks Need to solve #P? Let me know!