SlideShare a Scribd company logo
Neural network for black-box fusion of underwater
robot localization under unmodeled noise
19 sept 2019
Types of underwater vehicle
• Autonomus Underwater
Vehicle (AUV) with minor
or no intervention from
operator
• Remotely Operated
Vehicle (ROV) for
maintainance, repair
operations and sea
inspection
undewater environment and sensors
• rapid attenuation of higher
frequency signals and
unstructured nature of
water
• for postion and movement
acoustic, vision ,
accelerometer and
gyroscope sensors are
used
need of research
• there should be a neural
technique for sensory data
fusion
• coherently combining of
data(any) to estimation
location with respect to
reference frame
Acoustic sensors comparision 1/2
• cost functions (rate, reliability
etc)
• acustonic positioning sensors
provide asynchronous
mesurements
• estimates do not drift over time
in acoustic sensors so long
run measurement more
reliable
• slow signal traveling rate
(1500m/s)
acoustic sensory comparison 2/2
• geo refered landmark are
more reliable than acoustic
sensor
• commonly accoustic
(easy) LVS example
• robot have to come to
surface to reduce
localization uncertainty
main problem of fusion
• baysian algorithms(kalman
filters) are fine but estimation
perform poorly under
unmodeled noise
• parametric algorithms (MCL)
do multimodal hypothesis with
high computational cost
• problem is to make unimodel
estimates under unmodeled
noise
Approches for Problem 's solution 1/2
• model non linearity by
agumenting state representation
(difficult)
• supervied learning methodologies
in training of fusion algorithm for
correcting estimates (alternative)
{but for supervised learning task
condition should not vary in training
and execution time}
Approches for Problem 's solution 2/2
• Fusion of redundant
estimates of each sensor
based on error covarience
matrix (inversly or
covarience intersaction)
• fusion process as fuzzy
rule based system
(home example of neural
network training!!!!)
Writers' research focus
• developing heuristic and
generic fusion policy for
redundant estimates to
handle unmodeled noise
• proposed architecture
where redundant
estimates are viewed as
black box processes
Information fusion (past work same writer)
• principle of contexual information
anticipation for obtaining more
reliable fusion for egocentric
localization
• reliability is evalutated within
processing neighbourhood
(mean and deviation)
• confidence is in context of task
and nodes contrubution accordingly
weighted
Theory - Fusion architecture
• blue node has fusion
algorithm and weights
for each estimator
• Reset feature (blue node)
for reducing error (dead
recking replace with global
estimate) and context
transition according to
task
thory- fusion arhitecture- Parameter set
• µi(t) is mean state
estimate
• Σi(t) covarience matrix
related to error
• σi(t) is expected deviation
of neighbor node from
mean
• δti(t) is time interval
between two esimates
• i is process and t is time
theory - fusion architecture - ordering
arrangements1/2
• fusion node's ordering rule
depends on two
assumption
• A1: Estimates from non
delayed measurements
and follow unimodel
distribution(mean and
covariance matrix)
theory - fusion architecture - ordering arrangements
2/2
• A2: reliability in relation to
behaviour profile
(antisymetry, transitivity
and totality)
Theory - Modeling of A1 and A2
• assume set of one
dimentional site
arrangement (under B
profile)
• Sb is neighborhood
system
• relationship properties:
-no neighboring to itself
-neighboring relationship
is mutual
clinque left and right
Theory- Purpose of neural network
• To model arrangements
under distict behaviour
profile
• weighting information
from redundant
estimates to fusion
process
B-PR-F for neighboring arrangements
• Layer B is for behaviour
• Layer P is for prediction
• Layer R is for reliablity
• Layer F is for Fusion
B-PR-F layer B
• Task senerios and
conditions(near surface or
seabed) represented by
behavior profile
• cardinality is determined
by k availble behaviour
profiles
B-PR-F Layer P (imp noise)
• contextual anticipation b/w
neighborhood arrangements
• neurons here encode parameter
σi(t)
• σi(t) is expected deviation from
sorrounding µi(t) where estimate of
process i should fall
• activation becomes stronger and
uncertainty increasess as task
progesses (with motion of robot and
time pass)
B-PR-F Layer R
• encode confidence on
nodes's estimate in relation
to predicted value
• node passes the test and
related node is re-initialized
• cardinality is of PR layers
depends upon Behaviour
and estimators
B-PR-F Layer F
• contains fusion weight
for estimaters
• cardinality is determined
by n number of estimaters
• global estimated is
calculated by these
weighted sum
B-PR-F - Network parameters
• Wbp condition the activity of
PR layer according to B profile
• Wpp represent lateral
connection of layer P to model
the changes(due to B profile)
-no Interaction then Wpp is
identity otherwise
-f(arbitary func) is defined
according to task and estimator
parameters
B-PR-F - Network parameters
• Wpr connectivity between neighborhood
• ς is high magnitude assigned to
unrelated neighbors (inhibation)
• Wy is ordered arrangements of
nodes(according to B profile)
analytically stronger weights to clinque ,
excitatory weights to left and inhibitory
weights to right neighbor
• Wℵ(kxn) is provided by system designer
which tells reliability along behavior
profile
system configuration matrix
difference tells ordered
arrangements
B-PR-F Network parameters
• Wrf obtains from row of
system desinger matrix
• correspondance b/w sites
established through
maping function
(represented in PR and
estimators)
B-PR-F Layers(Behaviour) activation
• Winner takes all policy
• only one behavior at a
time
• arbitary function (self
defined that behaviour is
1 or 0)
B-PR-F Layers(Prediction) activation
• Activation of neurons in
layer P
• reset function cosider
reliability test applied to
right neighbor
• time scaling factor is
representing by heuristic
parameter
reset
function
time change
heuristic
parameter
** P node contains
deviation
B-PR-F Layers(Reliability) activation
• information is determined by left
neighbor's parameters
• activation of layer R
indication of new
estimator(given instant)
threshold
value
obtained from
left estimator
B-PR-F Layers(fusion) activation
• weighting the n estimators’
output proportionally to the
activation of Layer F (for u
and Σ )
Simulations -
Materials and methods
• simulation in Gazebo
• oceans waves senerio in robot
operating system
• dataset is of way point
trajectory
• robot to pass near way points
with particle physics engine(to
model dynamics from equatic
medium)
• Data generated is passed to GNU
Simulation - sensory details
• Predefined trajectory with
exploration mission of
shallow and deep water
• IMU for linear acceleration
and rotational rate(surface)
• DVL is more sophisticated in
deep water
• USBL and DGPS are
positioning sensors (in deep
water only usbl)
simulation results
• ALT for switching Behavior
profile
• IMU for near surface and
DVL for Deep water
produce precise result
• USBL can face issues (like
physical interference)
• BPRF eliminate noise of
virtual usbl sensor
Simulation results (behaviour 2)
• Principle of contextual
anticipation within ordered
neighborhood (only XY
axis)
• boundary of anticipated
region
{ r = p6(t)Σ2(t) i } encode
deviation of E3 with respect
to E2 estimate
simulation - Activation of layers
• evolution of layers for above
anticipated trajectory
• if usbl is within anticipated region
then reset signal for coresponding
node of P(anticipation in stand
deviation unit)
• neighbor arrangements and
evolution of info is encoded by
network
• F can reject unexpected
disturbance
simulation - activation of layers -
lateral connection role
• Wpp is set according to
two different condition
(identity and behavior
change)
• define sparse
encoding matrix (which
maps Behaviour a units to
Behviour z's)
Experience
• travelled 396 in 61 minutes
• Sonar tilt is 0 regarding horizon
• it can cover 130 horizon and 50
meters
• 19992 grayscale 16-bits images by
the SONAR
• 3663 leading values of compass
• 3662 positions by DGPS
• 1450 by USBL
Experimental Fusion of sensor
Experimental - localization -
scan matching motion estimation
• relative motion is from
multibeam sonar(no need
of correction)
• parameter of interest
• dead recking is obtained
by integrating relative
displacement over time
Experiment - Kalman filter
• F is state transition model
• x is estimated state vector
• B is control input model
• u is control control vector
• e is random gaussian
vector that model
uncertainties introduced by
state transition
• posterior state is corrected
by x P y S K
predicted state
estimate and
covariance

More Related Content

What's hot

RF Mixed Signal Guidi-McIllree-Stannard
RF Mixed Signal Guidi-McIllree-StannardRF Mixed Signal Guidi-McIllree-Stannard
RF Mixed Signal Guidi-McIllree-Stannard
John Stannard
 
TEMPEST AEM FORM 2000
TEMPEST AEM FORM 2000TEMPEST AEM FORM 2000
TEMPEST AEM FORM 2000
Brett Johnson
 
Presentation for the 21th EUROSTAR Users Conference - June 2013
Presentation for the 21th EUROSTAR Users Conference - June 2013 Presentation for the 21th EUROSTAR Users Conference - June 2013
Presentation for the 21th EUROSTAR Users Conference - June 2013
Antonios Arkas
 
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
grssieee
 
Advances in Satellite Conjunction Analysis with OR.A.SI
Advances in Satellite Conjunction Analysis with OR.A.SIAdvances in Satellite Conjunction Analysis with OR.A.SI
Advances in Satellite Conjunction Analysis with OR.A.SI
Antonios Arkas
 
Electromagnetic formationflight
Electromagnetic formationflightElectromagnetic formationflight
Electromagnetic formationflight
Clifford Stone
 
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
The HDF-EOS Tools and Information Center
 
Flight Dynamics Software Presentation Part II Version 7
Flight Dynamics Software Presentation Part II Version 7Flight Dynamics Software Presentation Part II Version 7
Flight Dynamics Software Presentation Part II Version 7
Antonios Arkas
 
Presentation for the 16th EUROSTAR Users Conference June 2008
Presentation for the 16th EUROSTAR Users Conference June 2008Presentation for the 16th EUROSTAR Users Conference June 2008
Presentation for the 16th EUROSTAR Users Conference June 2008
Antonios Arkas
 
Robotics Localization
Robotics LocalizationRobotics Localization
Robotics Localization
cairo university
 
3G Drive Test Procedure_ By Md Joynal Abaden
3G Drive Test Procedure_ By Md Joynal Abaden3G Drive Test Procedure_ By Md Joynal Abaden
3G Drive Test Procedure_ By Md Joynal Abaden
Md Joynal Abaden
 
Presentation for the 19th EUROSTAR Users Conference June 2011
Presentation for the 19th EUROSTAR Users Conference June 2011Presentation for the 19th EUROSTAR Users Conference June 2011
Presentation for the 19th EUROSTAR Users Conference June 2011
Antonios Arkas
 
LEO OR.A.SI Presentation Version No.17
LEO OR.A.SI Presentation Version No.17LEO OR.A.SI Presentation Version No.17
LEO OR.A.SI Presentation Version No.17
Antonios Arkas
 
Observability of path loss parameters in wlan based simultaneous
Observability of path loss parameters in wlan based simultaneousObservability of path loss parameters in wlan based simultaneous
Observability of path loss parameters in wlan based simultaneous
lbruno236
 
DQN Variants: A quick glance
DQN Variants: A quick glanceDQN Variants: A quick glance
DQN Variants: A quick glance
Tejas Kotha
 
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
csandit
 
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONSDUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
jantjournal
 

What's hot (17)

RF Mixed Signal Guidi-McIllree-Stannard
RF Mixed Signal Guidi-McIllree-StannardRF Mixed Signal Guidi-McIllree-Stannard
RF Mixed Signal Guidi-McIllree-Stannard
 
TEMPEST AEM FORM 2000
TEMPEST AEM FORM 2000TEMPEST AEM FORM 2000
TEMPEST AEM FORM 2000
 
Presentation for the 21th EUROSTAR Users Conference - June 2013
Presentation for the 21th EUROSTAR Users Conference - June 2013 Presentation for the 21th EUROSTAR Users Conference - June 2013
Presentation for the 21th EUROSTAR Users Conference - June 2013
 
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
SandbergImpactandModelingofTopographicEffectsonPBandSARBackscatterFromBorealF...
 
Advances in Satellite Conjunction Analysis with OR.A.SI
Advances in Satellite Conjunction Analysis with OR.A.SIAdvances in Satellite Conjunction Analysis with OR.A.SI
Advances in Satellite Conjunction Analysis with OR.A.SI
 
Electromagnetic formationflight
Electromagnetic formationflightElectromagnetic formationflight
Electromagnetic formationflight
 
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
The LEISA Atmospheric Corrector (LAC) on Earth Observer 1 (EO1)
 
Flight Dynamics Software Presentation Part II Version 7
Flight Dynamics Software Presentation Part II Version 7Flight Dynamics Software Presentation Part II Version 7
Flight Dynamics Software Presentation Part II Version 7
 
Presentation for the 16th EUROSTAR Users Conference June 2008
Presentation for the 16th EUROSTAR Users Conference June 2008Presentation for the 16th EUROSTAR Users Conference June 2008
Presentation for the 16th EUROSTAR Users Conference June 2008
 
Robotics Localization
Robotics LocalizationRobotics Localization
Robotics Localization
 
3G Drive Test Procedure_ By Md Joynal Abaden
3G Drive Test Procedure_ By Md Joynal Abaden3G Drive Test Procedure_ By Md Joynal Abaden
3G Drive Test Procedure_ By Md Joynal Abaden
 
Presentation for the 19th EUROSTAR Users Conference June 2011
Presentation for the 19th EUROSTAR Users Conference June 2011Presentation for the 19th EUROSTAR Users Conference June 2011
Presentation for the 19th EUROSTAR Users Conference June 2011
 
LEO OR.A.SI Presentation Version No.17
LEO OR.A.SI Presentation Version No.17LEO OR.A.SI Presentation Version No.17
LEO OR.A.SI Presentation Version No.17
 
Observability of path loss parameters in wlan based simultaneous
Observability of path loss parameters in wlan based simultaneousObservability of path loss parameters in wlan based simultaneous
Observability of path loss parameters in wlan based simultaneous
 
DQN Variants: A quick glance
DQN Variants: A quick glanceDQN Variants: A quick glance
DQN Variants: A quick glance
 
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
 
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONSDUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
DUAL BAND GNSS ANTENNA PHASE CENTER CHARACTERIZATION FOR AUTOMOTIVE APPLICATIONS
 

Similar to Neural network for black-box fusion of underwater robot localization under unmodeled noise

Grid Based Fuzzy Optimized Routing Protocol for Under Water Sensor Network
Grid Based Fuzzy Optimized  Routing Protocol for  Under Water Sensor Network Grid Based Fuzzy Optimized  Routing Protocol for  Under Water Sensor Network
Grid Based Fuzzy Optimized Routing Protocol for Under Water Sensor Network
Zakaria Shuvo
 
Pointtopointmicrowave 100826070651-phpapp02
Pointtopointmicrowave 100826070651-phpapp02Pointtopointmicrowave 100826070651-phpapp02
Pointtopointmicrowave 100826070651-phpapp02
Neerajku Samal
 
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPSSATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
Arkaprava Jana
 
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
Abdul Qudoos
 
53_36765_ME591_2012_1__1_1_SENSORS.pdf
53_36765_ME591_2012_1__1_1_SENSORS.pdf53_36765_ME591_2012_1__1_1_SENSORS.pdf
53_36765_ME591_2012_1__1_1_SENSORS.pdf
DrPArivalaganASSTPRO
 
Evaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs localEvaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs local
IAEME Publication
 
Evaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs localEvaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs local
IAEME Publication
 
mnNOG 2023: On GEOs, LEOs and Starlink
mnNOG 2023: On GEOs, LEOs and StarlinkmnNOG 2023: On GEOs, LEOs and Starlink
mnNOG 2023: On GEOs, LEOs and Starlink
APNIC
 
Radio Resource Management for Millimeter Wave & Massive MIMO
Radio Resource Management for Millimeter Wave & Massive MIMORadio Resource Management for Millimeter Wave & Massive MIMO
Radio Resource Management for Millimeter Wave & Massive MIMO
Eduardo Castañeda
 
Digital signal transmission in ofc
Digital signal transmission in ofcDigital signal transmission in ofc
Digital signal transmission in ofc
Ankith Shetty
 
Network layer
Network layerNetwork layer
Network layer
TharuniDiddekunta
 
Global Map Matching using BLE Beacons for Indoor Route and Stay Estimation
Global Map Matching using BLE Beacons for Indoor Route and Stay EstimationGlobal Map Matching using BLE Beacons for Indoor Route and Stay Estimation
Global Map Matching using BLE Beacons for Indoor Route and Stay Estimation
Daisuke Yamamoto
 
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
grssieee
 
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
ebhark
 
Optical satellite communication
Optical satellite communicationOptical satellite communication
Optical satellite communication
Bharat Rathore
 
computer communications
computer communicationscomputer communications
computer communications
JAYASHSINGHRA2111003
 
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP) MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
Electronics & Communication Staff SCU Suez Canal University
 
Load flow analysis of radial distribution system
Load flow analysis of radial distribution system Load flow analysis of radial distribution system
Load flow analysis of radial distribution system
Siksha 'O' Anusandhan (Deemed to be University )
 
routing algo n
routing algo                                nrouting algo                                n
routing algo n
SwatiHans10
 
Multiple UGV SLAM Map Sharing
Multiple UGV SLAM Map SharingMultiple UGV SLAM Map Sharing
Multiple UGV SLAM Map Sharing
Akash Borate
 

Similar to Neural network for black-box fusion of underwater robot localization under unmodeled noise (20)

Grid Based Fuzzy Optimized Routing Protocol for Under Water Sensor Network
Grid Based Fuzzy Optimized  Routing Protocol for  Under Water Sensor Network Grid Based Fuzzy Optimized  Routing Protocol for  Under Water Sensor Network
Grid Based Fuzzy Optimized Routing Protocol for Under Water Sensor Network
 
Pointtopointmicrowave 100826070651-phpapp02
Pointtopointmicrowave 100826070651-phpapp02Pointtopointmicrowave 100826070651-phpapp02
Pointtopointmicrowave 100826070651-phpapp02
 
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPSSATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
SATELLITE COMMUNICATION AND IT'S APPLICATION IN GPS
 
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
Dynamic sub arrays for Hybrid Precoding in Wide Band Millimeter Wave Wireless...
 
53_36765_ME591_2012_1__1_1_SENSORS.pdf
53_36765_ME591_2012_1__1_1_SENSORS.pdf53_36765_ME591_2012_1__1_1_SENSORS.pdf
53_36765_ME591_2012_1__1_1_SENSORS.pdf
 
Evaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs localEvaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs local
 
Evaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs localEvaluation of remote sensing satellite ground station performance in prbs local
Evaluation of remote sensing satellite ground station performance in prbs local
 
mnNOG 2023: On GEOs, LEOs and Starlink
mnNOG 2023: On GEOs, LEOs and StarlinkmnNOG 2023: On GEOs, LEOs and Starlink
mnNOG 2023: On GEOs, LEOs and Starlink
 
Radio Resource Management for Millimeter Wave & Massive MIMO
Radio Resource Management for Millimeter Wave & Massive MIMORadio Resource Management for Millimeter Wave & Massive MIMO
Radio Resource Management for Millimeter Wave & Massive MIMO
 
Digital signal transmission in ofc
Digital signal transmission in ofcDigital signal transmission in ofc
Digital signal transmission in ofc
 
Network layer
Network layerNetwork layer
Network layer
 
Global Map Matching using BLE Beacons for Indoor Route and Stay Estimation
Global Map Matching using BLE Beacons for Indoor Route and Stay EstimationGlobal Map Matching using BLE Beacons for Indoor Route and Stay Estimation
Global Map Matching using BLE Beacons for Indoor Route and Stay Estimation
 
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
QUALITY ASSESSMENT FOR LIDAR POINT CLOUD REGISTRATION USING IN-SITU CONJUGATE...
 
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
Bhark, E.W., Texas A&M MCERI, Norne Field reservoir model characterization wo...
 
Optical satellite communication
Optical satellite communicationOptical satellite communication
Optical satellite communication
 
computer communications
computer communicationscomputer communications
computer communications
 
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP) MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
MIMO Evolution: Coordinated Multi Point Transmission / reception (COMP)
 
Load flow analysis of radial distribution system
Load flow analysis of radial distribution system Load flow analysis of radial distribution system
Load flow analysis of radial distribution system
 
routing algo n
routing algo                                nrouting algo                                n
routing algo n
 
Multiple UGV SLAM Map Sharing
Multiple UGV SLAM Map SharingMultiple UGV SLAM Map Sharing
Multiple UGV SLAM Map Sharing
 

More from umairali255

8x3x8 Multi layer perceptron training using Python Code
8x3x8 Multi layer perceptron training using Python Code8x3x8 Multi layer perceptron training using Python Code
8x3x8 Multi layer perceptron training using Python Code
umairali255
 
Perceptrons
PerceptronsPerceptrons
Perceptrons
umairali255
 
weights training of perceptron (using 3 training rules)
weights training of perceptron (using 3 training rules)weights training of perceptron (using 3 training rules)
weights training of perceptron (using 3 training rules)
umairali255
 
Diode thyristor transistor
Diode thyristor transistorDiode thyristor transistor
Diode thyristor transistor
umairali255
 
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
umairali255
 
novel approach for charger of electrical vehicle
novel approach for charger of electrical vehiclenovel approach for charger of electrical vehicle
novel approach for charger of electrical vehicle
umairali255
 
IMU and LiDar vision system using Neural network
IMU and LiDar vision system using Neural networkIMU and LiDar vision system using Neural network
IMU and LiDar vision system using Neural network
umairali255
 
why and where use Advance power electronics design
why and where use Advance power electronics design why and where use Advance power electronics design
why and where use Advance power electronics design
umairali255
 

More from umairali255 (8)

8x3x8 Multi layer perceptron training using Python Code
8x3x8 Multi layer perceptron training using Python Code8x3x8 Multi layer perceptron training using Python Code
8x3x8 Multi layer perceptron training using Python Code
 
Perceptrons
PerceptronsPerceptrons
Perceptrons
 
weights training of perceptron (using 3 training rules)
weights training of perceptron (using 3 training rules)weights training of perceptron (using 3 training rules)
weights training of perceptron (using 3 training rules)
 
Diode thyristor transistor
Diode thyristor transistorDiode thyristor transistor
Diode thyristor transistor
 
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
Novel Terrain Integrated Navigation System using Neural Network aided Kalman ...
 
novel approach for charger of electrical vehicle
novel approach for charger of electrical vehiclenovel approach for charger of electrical vehicle
novel approach for charger of electrical vehicle
 
IMU and LiDar vision system using Neural network
IMU and LiDar vision system using Neural networkIMU and LiDar vision system using Neural network
IMU and LiDar vision system using Neural network
 
why and where use Advance power electronics design
why and where use Advance power electronics design why and where use Advance power electronics design
why and where use Advance power electronics design
 

Recently uploaded

OOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming languageOOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming language
PreethaV16
 
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
PriyankaKilaniya
 
Ericsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.pptEricsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.ppt
wafawafa52
 
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
upoux
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
VANDANAMOHANGOUDA
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
OKORIE1
 
SCALING OF MOS CIRCUITS m .pptx
SCALING OF MOS CIRCUITS m                 .pptxSCALING OF MOS CIRCUITS m                 .pptx
SCALING OF MOS CIRCUITS m .pptx
harshapolam10
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 
Supermarket Management System Project Report.pdf
Supermarket Management System Project Report.pdfSupermarket Management System Project Report.pdf
Supermarket Management System Project Report.pdf
Kamal Acharya
 
Bituminous road construction project based learning report
Bituminous road construction project based learning reportBituminous road construction project based learning report
Bituminous road construction project based learning report
CE19KaushlendraKumar
 
Levelised Cost of Hydrogen (LCOH) Calculator Manual
Levelised Cost of Hydrogen  (LCOH) Calculator ManualLevelised Cost of Hydrogen  (LCOH) Calculator Manual
Levelised Cost of Hydrogen (LCOH) Calculator Manual
Massimo Talia
 
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Transcat
 
Call For Paper -3rd International Conference on Artificial Intelligence Advan...
Call For Paper -3rd International Conference on Artificial Intelligence Advan...Call For Paper -3rd International Conference on Artificial Intelligence Advan...
Call For Paper -3rd International Conference on Artificial Intelligence Advan...
ijseajournal
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
Kamal Acharya
 
Generative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdfGenerative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdf
mahaffeycheryld
 
Power Electronics- AC -AC Converters.pptx
Power Electronics- AC -AC Converters.pptxPower Electronics- AC -AC Converters.pptx
Power Electronics- AC -AC Converters.pptx
Poornima D
 
Impartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 StandardImpartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 Standard
MuhammadJazib15
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
uqyfuc
 
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
DharmaBanothu
 
P5 Working Drawings.pdf floor plan, civil
P5 Working Drawings.pdf floor plan, civilP5 Working Drawings.pdf floor plan, civil
P5 Working Drawings.pdf floor plan, civil
AnasAhmadNoor
 

Recently uploaded (20)

OOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming languageOOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming language
 
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
 
Ericsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.pptEricsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.ppt
 
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
 
SCALING OF MOS CIRCUITS m .pptx
SCALING OF MOS CIRCUITS m                 .pptxSCALING OF MOS CIRCUITS m                 .pptx
SCALING OF MOS CIRCUITS m .pptx
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 
Supermarket Management System Project Report.pdf
Supermarket Management System Project Report.pdfSupermarket Management System Project Report.pdf
Supermarket Management System Project Report.pdf
 
Bituminous road construction project based learning report
Bituminous road construction project based learning reportBituminous road construction project based learning report
Bituminous road construction project based learning report
 
Levelised Cost of Hydrogen (LCOH) Calculator Manual
Levelised Cost of Hydrogen  (LCOH) Calculator ManualLevelised Cost of Hydrogen  (LCOH) Calculator Manual
Levelised Cost of Hydrogen (LCOH) Calculator Manual
 
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
 
Call For Paper -3rd International Conference on Artificial Intelligence Advan...
Call For Paper -3rd International Conference on Artificial Intelligence Advan...Call For Paper -3rd International Conference on Artificial Intelligence Advan...
Call For Paper -3rd International Conference on Artificial Intelligence Advan...
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
 
Generative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdfGenerative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdf
 
Power Electronics- AC -AC Converters.pptx
Power Electronics- AC -AC Converters.pptxPower Electronics- AC -AC Converters.pptx
Power Electronics- AC -AC Converters.pptx
 
Impartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 StandardImpartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 Standard
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
 
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
A high-Speed Communication System is based on the Design of a Bi-NoC Router, ...
 
P5 Working Drawings.pdf floor plan, civil
P5 Working Drawings.pdf floor plan, civilP5 Working Drawings.pdf floor plan, civil
P5 Working Drawings.pdf floor plan, civil
 

Neural network for black-box fusion of underwater robot localization under unmodeled noise

  • 1. Neural network for black-box fusion of underwater robot localization under unmodeled noise 19 sept 2019
  • 2. Types of underwater vehicle • Autonomus Underwater Vehicle (AUV) with minor or no intervention from operator • Remotely Operated Vehicle (ROV) for maintainance, repair operations and sea inspection
  • 3. undewater environment and sensors • rapid attenuation of higher frequency signals and unstructured nature of water • for postion and movement acoustic, vision , accelerometer and gyroscope sensors are used
  • 4. need of research • there should be a neural technique for sensory data fusion • coherently combining of data(any) to estimation location with respect to reference frame
  • 5. Acoustic sensors comparision 1/2 • cost functions (rate, reliability etc) • acustonic positioning sensors provide asynchronous mesurements • estimates do not drift over time in acoustic sensors so long run measurement more reliable • slow signal traveling rate (1500m/s)
  • 6. acoustic sensory comparison 2/2 • geo refered landmark are more reliable than acoustic sensor • commonly accoustic (easy) LVS example • robot have to come to surface to reduce localization uncertainty
  • 7. main problem of fusion • baysian algorithms(kalman filters) are fine but estimation perform poorly under unmodeled noise • parametric algorithms (MCL) do multimodal hypothesis with high computational cost • problem is to make unimodel estimates under unmodeled noise
  • 8. Approches for Problem 's solution 1/2 • model non linearity by agumenting state representation (difficult) • supervied learning methodologies in training of fusion algorithm for correcting estimates (alternative) {but for supervised learning task condition should not vary in training and execution time}
  • 9. Approches for Problem 's solution 2/2 • Fusion of redundant estimates of each sensor based on error covarience matrix (inversly or covarience intersaction) • fusion process as fuzzy rule based system (home example of neural network training!!!!)
  • 10. Writers' research focus • developing heuristic and generic fusion policy for redundant estimates to handle unmodeled noise • proposed architecture where redundant estimates are viewed as black box processes
  • 11. Information fusion (past work same writer) • principle of contexual information anticipation for obtaining more reliable fusion for egocentric localization • reliability is evalutated within processing neighbourhood (mean and deviation) • confidence is in context of task and nodes contrubution accordingly weighted
  • 12. Theory - Fusion architecture • blue node has fusion algorithm and weights for each estimator • Reset feature (blue node) for reducing error (dead recking replace with global estimate) and context transition according to task
  • 13. thory- fusion arhitecture- Parameter set • µi(t) is mean state estimate • Σi(t) covarience matrix related to error • σi(t) is expected deviation of neighbor node from mean • δti(t) is time interval between two esimates • i is process and t is time
  • 14. theory - fusion architecture - ordering arrangements1/2 • fusion node's ordering rule depends on two assumption • A1: Estimates from non delayed measurements and follow unimodel distribution(mean and covariance matrix)
  • 15. theory - fusion architecture - ordering arrangements 2/2 • A2: reliability in relation to behaviour profile (antisymetry, transitivity and totality)
  • 16. Theory - Modeling of A1 and A2 • assume set of one dimentional site arrangement (under B profile) • Sb is neighborhood system • relationship properties: -no neighboring to itself -neighboring relationship is mutual clinque left and right
  • 17. Theory- Purpose of neural network • To model arrangements under distict behaviour profile • weighting information from redundant estimates to fusion process
  • 18. B-PR-F for neighboring arrangements • Layer B is for behaviour • Layer P is for prediction • Layer R is for reliablity • Layer F is for Fusion
  • 19. B-PR-F layer B • Task senerios and conditions(near surface or seabed) represented by behavior profile • cardinality is determined by k availble behaviour profiles
  • 20. B-PR-F Layer P (imp noise) • contextual anticipation b/w neighborhood arrangements • neurons here encode parameter σi(t) • σi(t) is expected deviation from sorrounding µi(t) where estimate of process i should fall • activation becomes stronger and uncertainty increasess as task progesses (with motion of robot and time pass)
  • 21. B-PR-F Layer R • encode confidence on nodes's estimate in relation to predicted value • node passes the test and related node is re-initialized • cardinality is of PR layers depends upon Behaviour and estimators
  • 22. B-PR-F Layer F • contains fusion weight for estimaters • cardinality is determined by n number of estimaters • global estimated is calculated by these weighted sum
  • 23. B-PR-F - Network parameters • Wbp condition the activity of PR layer according to B profile • Wpp represent lateral connection of layer P to model the changes(due to B profile) -no Interaction then Wpp is identity otherwise -f(arbitary func) is defined according to task and estimator parameters
  • 24. B-PR-F - Network parameters • Wpr connectivity between neighborhood • ς is high magnitude assigned to unrelated neighbors (inhibation) • Wy is ordered arrangements of nodes(according to B profile) analytically stronger weights to clinque , excitatory weights to left and inhibitory weights to right neighbor • Wℵ(kxn) is provided by system designer which tells reliability along behavior profile system configuration matrix difference tells ordered arrangements
  • 25. B-PR-F Network parameters • Wrf obtains from row of system desinger matrix • correspondance b/w sites established through maping function (represented in PR and estimators)
  • 26. B-PR-F Layers(Behaviour) activation • Winner takes all policy • only one behavior at a time • arbitary function (self defined that behaviour is 1 or 0)
  • 27. B-PR-F Layers(Prediction) activation • Activation of neurons in layer P • reset function cosider reliability test applied to right neighbor • time scaling factor is representing by heuristic parameter reset function time change heuristic parameter ** P node contains deviation
  • 28. B-PR-F Layers(Reliability) activation • information is determined by left neighbor's parameters • activation of layer R indication of new estimator(given instant) threshold value obtained from left estimator
  • 29. B-PR-F Layers(fusion) activation • weighting the n estimators’ output proportionally to the activation of Layer F (for u and Σ )
  • 30. Simulations - Materials and methods • simulation in Gazebo • oceans waves senerio in robot operating system • dataset is of way point trajectory • robot to pass near way points with particle physics engine(to model dynamics from equatic medium) • Data generated is passed to GNU
  • 31. Simulation - sensory details • Predefined trajectory with exploration mission of shallow and deep water • IMU for linear acceleration and rotational rate(surface) • DVL is more sophisticated in deep water • USBL and DGPS are positioning sensors (in deep water only usbl)
  • 32. simulation results • ALT for switching Behavior profile • IMU for near surface and DVL for Deep water produce precise result • USBL can face issues (like physical interference) • BPRF eliminate noise of virtual usbl sensor
  • 33. Simulation results (behaviour 2) • Principle of contextual anticipation within ordered neighborhood (only XY axis) • boundary of anticipated region { r = p6(t)Σ2(t) i } encode deviation of E3 with respect to E2 estimate
  • 34. simulation - Activation of layers • evolution of layers for above anticipated trajectory • if usbl is within anticipated region then reset signal for coresponding node of P(anticipation in stand deviation unit) • neighbor arrangements and evolution of info is encoded by network • F can reject unexpected disturbance
  • 35. simulation - activation of layers - lateral connection role • Wpp is set according to two different condition (identity and behavior change) • define sparse encoding matrix (which maps Behaviour a units to Behviour z's)
  • 36. Experience • travelled 396 in 61 minutes • Sonar tilt is 0 regarding horizon • it can cover 130 horizon and 50 meters • 19992 grayscale 16-bits images by the SONAR • 3663 leading values of compass • 3662 positions by DGPS • 1450 by USBL
  • 38. Experimental - localization - scan matching motion estimation • relative motion is from multibeam sonar(no need of correction) • parameter of interest • dead recking is obtained by integrating relative displacement over time
  • 39. Experiment - Kalman filter • F is state transition model • x is estimated state vector • B is control input model • u is control control vector • e is random gaussian vector that model uncertainties introduced by state transition • posterior state is corrected by x P y S K predicted state estimate and covariance