Adapting%20Ocean%20Surveys%20to%20the%20Observed%20Fields%20Characteristics

1
Adapting Ocean Surveys to the Observed Fields
Characteristics

• Maria-João Rendas
• I3S, CNRS-UNSA

2
Outline

• The goals of Sumare
• Using prior information
• Exploiting reactive behaviors
• Conclusions and perspectives

3
The goals of SUMARE
design strategies for environmental monitoring
using autonomous sensors

• Traditional means
• Oceanographic ships networks of buoys divers
• A priori determination of the surveyed region and
  of the spatial sampling rate
• Difficult to focus on features of interest.
• Limited operating conditions (shallow waters,
  under ice, ....)

• Autonomous sensors
• Sensors carried by mobile robots (cheaper, easier
  to operate)
• Sensor trajectory can be determined on-line
  during survey
• Ability to concentrate (track) features of
  interest
• Wide range of operating scenarios

test their added-value in two applications sand
bank and maerl mapping
4
Two approaches

• Exploiting prior knowledge
• give to the sensor a mathematical (statistical)
  model of the possible appearances of the field
• use data together with the prior model to
  extrapolate the data in the observed region over
  an extended domain

• Exploiting reactive behaviour
• track interesting features (contours, canyons,
  iso-depth lines,...)
• adapt the spatial sampling rate
• identify the regions which are more informative
  with respect to the end-users goals.
• use environments features to navigate,
  decreasing dependability on artificial references
  or surfacing for GPS fixes

5
Using prior knowledge
Goal efficiently use prior knowledge about the
observed field (which constrains the possible set
of actually occuring field patterns) Efficiency
gain comes from being able to extrapolate across
spatial regions, and to direct the sensor
to the most informative regions
?
6

• Case studies
• current fields (mouth of the Rhone river)
• sand banks (Kwintebank, Belgium)

7
Current fields
Problem map a natural field (currents in the
mouth of the river Rhone) Framework Bayesian
(use prior knowledge to characterize the set of
possible observed maps) Prior knowledge
predictions made using mathematical models
(MUMM) (Navier-Stokes equation)
8

A PRIORI KNOWLEDGE
41 maps (15 x 22 grid)
provided by MUMM (Brussels, Belgium) 10 maps
reserved for testing
9
KNOWLEDGE REPRESENTATION

• Learn from data
• Geometric model
• c Va Ue, VTU0
• Statistical model
• a N(ma, diag(li))
• N(0, lL1I)
• ?
• c N(VmaVT, VSaVTSe)

10

EXTRAPOLATION
Allows extrapolation of local observations

Maximum a posteriori estimate
11

Uncertainty of the resulting field can be
determined
showing how matrix S (the choice of observation
points) impacts performance
12
INFORMATION GAIN
Points can be chosen (a priori) to maximise
overall expected information gain (minimize the
covariance of the a posteriori estimate)
13
INFORMATION GUIDANCE
If only a specific feature is of interest (e.g. a
given contour level) its uncertainty can be
computed, and the vehicle guided in order to
optimise its observation performance
Example map the line of constant current
intensity cCte
14
Local minimax criterion optimize the accuracy
of the worst estimated neighbour contour point
Using a 1st order Taylor expansion
15
Adaptive determination of next observation
point ? - robot position ? - best identified
point
trajectory
true contour estimated contour (using current
values observed along trajectory and prior
statistical model)
16
Sand bank profiles
Problem observation of the variation of sand
bank profiles (Kwintebank, Belgium) Prior
knowledge observations (oceanographic surveys)
provided by MUMM.
17
(No Transcript)
18
(No Transcript)
19
(No Transcript)
20
Reconstruction
Low-dimensional statistical model learned from
data set using a wavelet representation of the
profiles
21
(No Transcript)
22
(No Transcript)
23

• Approach
• build (for each profile) a statistical model of
  the variations of the profile with respect to the
  average profile
• use this model to extrapolate across distinct
  regions of the profile, and to identify the most
  informative sections.

Problem Which interval of length I provides,
according to the identified model, the largest
information with respect to the total volume?
What is the uncertainty of the volume estimate
given those observations ? Can we repeat this
step iteratively, identifying the next better
region on the basis of the already observed
regions ?
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
Observation strategies
Design of observation strategies is meaningless
for one-dimensional observation spaces
(lines). Full 2½D statistical model of the
Kwintebank will be learned, and adaptive
observation algorithms will be designed on the
basis of the learned statistical model. For the
sand bank, since it is a dynamical phenomenon, it
makes more sense to learn a model of the
variations than of the shape of the bank itself.
28
Exploiting reactive behavior
Directly acquire distinctive features of the
environment
29
Classification of sea-bottom
Allows on-line guidance based on the sea-bed
occupancy. Requires training data to recognize
the type of bottom Provides direct geometric
features that allow the navigation of the robot
with respect to natural features
30
(No Transcript)