Situation Awareness in Cyber-Physical Systems using Indoor Localization and Semantic Data Abstraction

Department ofElectrical Engineering

Situation Awareness in Cyber-Physical Systems using Indoor Localization and Semantic Data Abstraction

Presenter Pratikkumar Desai

Advisor Dr. Kuldip Rattan

PhD Seminar - 11/2/2012


Outline• Introduction

• Cyber-Physical System• Situation Awareness

• Motivation• Problem Statement• Semantic Sensor Web• Indoor Localization

Domain: Cyber-physical SystemsApplication: Situation Awareness


Cyber-Physical SystemsCyber : Computation, communication, and control that are discrete, logical, and switchedPhysical : Natural and human-made systems governed by the laws of physics and operating in continuous timeCyber-Physical Systems (CPS) : Systems in which the cyber and physical systems are tightly integrated at all scales and levels

What it is not?• Not desktop computing • Not traditional embedded/real-time systems • Not today’s sensor nets


CPS Examples

eHealth

Military

Smart Home


Situation Awareness

Projection

of the future

state or actions

Comprehension of the current situation

Perception of the elements in the current situation


Motivation Scenario

• Responders are using sensor equipped mobile robot.• Building is equipped with a system which can provide location.• Need to Identify the situation from available sensor data.• Need to identify location of the event.

First responders(Hazardous condition)


Perceptions & Comprehensions

• Sensors on Mobile Robot:• Temperature• Pressure• Humidity• CO2

• CO• Chemical sensors

• Sensors in home:• Fire alarm• Thermostat

• Human observation• Background knowledge

• Fire:• Gas• Liquid• Wood• Mix

• Dry heat• Dry Ice• False Alarm• Chemical leakage


Information Overload


Problem Statements(1) Reduce information overload on the operatorSolutions:

• Semantic abstractions of sensor data• Semantic Sensor Web based automatic event comprehension

(2) Identify the location of the eventSolution:

• Indoor localization in GPS denied environments


Semantic Sensor Web


Semantic Web“The Semantic Web is a major research initiative of the World Wide Web Consortium (W3C) to create a metadata-rich Web of resources that can describe themselves not only by how they should be displayed (HTML) or syntactically (XML), but also by the meaning of the metadata.”

From W3C Semantic Web Activity Page

“The Semantic Web is an extension of the current web in which information is given well-defined meaning, better enabling computers and people to work in cooperation.”

Tim Berners-Lee, James Hendler, Ora Lassila, The Semantic Web, Scientific American, May 2001

http://www.scientificamerican.com/article.cfm?articleID=00048144-10D2-1C70-84A9809EC588EF21&catID=2


Semantic Sensor Web

• An approach of annotating raw sensor data with semantic, spatial and temporal metadata to increase interoperability.

• Provide abstraction to low level sensor data for more intuitive representation.

• Provide Comprehension abstractions for event identification.


Cyber-Physical Systems for Situation Awareness

Semantic Sensor Web


System Architecture of Semantic Web Implementation


Abstraction

Bipartite Graph Sensor Perception and Event comprehension abstractionsfor the Example Scenario


Detecting a Fire• Temperature (local, on robot):

= 100 C

• Temperature (IR):= 150 C

• IR light (looking straight):= 800

• IR light (looking down):= 800

• Carbon Dioxide:= 2000 ppm


Simulation Results

RobotFire


Future Work

Unknown Event• Temperature (local, on robot):

= 100 C

• Temperature (IR):= 22 C

• IR light (looking straight):= 0

• IR light (looking down):= 800

• Carbon Dioxide:= 2000 ppm


Future Work

Fuzzy Abstraction Set

• Fuzzy abstraction sets can be useful in handling the problem of uncertain perception conditions.

• An uncertain sensor perception can infer more than one situation in some cases.


Indoor Localization


GPS denied Environments


Traditional Indoor Localization Techniques

• Active Badge and Active Bat system.

• RADAR: An In-building RF-based user location and tracking system.

• RFID radar

• Object tracking with multiple cameras• Computer vision based localization

• Wireless Sensor Network

RF

Camera

TDoA


The Cricket Motes

• High performance MICA2 wireless location system.• Ultrasound transmitter and receiver for time of flight

ranging.• Decentralized and scalable operation.

• Applications:-• Indoor location system• Ubiquitous computing• Asset/person tracking


Beacon & Listener

Ceiling

floor

Beacons• Static• Pseudo-Satellites

Listeners• Dynamic• Receivers


TDoA in The Cricket System


Localization: TrilaterationNumber of nodes = 3.

Outlier Rejection and Multilateration are used to improve location results.


Pros

• Distance estimation accuracy is less than 2 cm for 10 meters.

• Appropriate for localizing • small vehicles such as Mobile

robots or a person.• Least expensive.

Cons

• Always need Line-of-Sight• (LOS) for distance estimation.• Do not work in presence• of ultrasonic noise.• Slow update rate for dynamic

application.

TDoA Based Positioning System


The Proposed Algorithm• Utilizes fusion of RSSI and TDoA data for accurate

distance estimation.• The algorithm stages,

• RSSI data training• Distance estimation• Localization

• Uses TDoA as a primary distance estimation technique.• RSSI data is trained and converted into appropriate

distance measurements.• The proposed algorithm can be used in absence of one or

many TDoA links.


Initial Conditions

• Distances between all beacons are known and fixed


0 ? ? ?? 0 ? ?? ? 0 ?? ? ? 0

L

B4

B2

B3

B1

0 ? ? ?? 0 ? ?? ? 0 ?

R14 ? ? 0

0 ? ? ?R12 0 ? ?? ? 0 ?? ? ? 0

0 ? ? ?? 0 ? ?

R13 ? 0 ?? ? ? 0

0 ? ? ? R1L T1L

? 0 ? ? ? ?? ? 0 ? ? ?? ? ? 0 ? ?

RSSI LinkTDoA Link

Beacon B1 Transmit Data


0 R21 R31 R41

R12 0 ? ?R13 R23 0 ?R14 R24 R34 0

L

B4

B2

B3

B1

0 ? ? ?R12 0 ? ?R13 R23 0 ?R14 R24 R34 0

0 ? ? ?R12 0 R32 R42

R13 R23 0 ?R14 R24 R34 0

0 ? ? ?R12 0 ? ?R13 R23 0 R43

R14 R24 R34 0

0 ? ? ? R1L T1L

R12 0 ? ? R2L T2L

R13 R23 0 ? R3L T3L

R14 R24 R34 0 R4L T4L

RSSI LinkTDoA Link

Beacon B4 Transmit Data


Distance Estimation (i)• In traditional RSSI based estimation schemes, distance is

estimated with following equation,

Where, A is an environment loss factor

ˆ Ad

RSSI

2r

2 2

P( )

(4 )t r

t

GGd

P d L

22

2

1ˆ(4 )t r tGG P

dL RSSI


Distance Estimation (ii)• The algorithm proposes, ‘A’ to be a variable which is dependent upon multi-

path propagation and other environmental variables.

• ‘A’ can obtained from below equation,

• The estimated value of ‘’ is then used to calculate distance in absence of TDoA link, using following equation,

Where, ‘n’ is number of data collected

ˆˆtrained

Ad

RSSI


IPS Results – Proposed AlgorithmRMS error in position estimation

(using proposed algorithm).


Summary• An approach of solving future situation awareness

problems using Cyber-Physical Systems.

• Introduced Semantic Web based sensor data abstraction to reduced the operator information overload.

• A novel indoor localization algorithm to pinpoint the location of event being monitored.


Acknowledgement• Dr. Kuldip Rattan (Advisor)• Dr. Amit Sheth ( Co-advisor / Director, Kno.e.sis)


Questions ?


Demo[If time permits]

SECURE : Semantic Empowered resCUe enviRonmEnt

http://www.youtube.com/watch?v=gHn9aCt9zQU%23t=42s

Documents

Situation Awareness in Cyber-Physical Systems using Indoor Localization and Semantic Data Abstraction