SLIDE 1 Robust ¡indoor ¡loca/on ¡tracking ¡
via ¡interval ¡analysis ¡
- Mohamed-‑Hédi ¡AMRI, ¡Yasmina ¡BECIS, ¡
Didier ¡AUBRY ¡& ¡ ¡Nacim ¡RAMDANI ¡
Université ¡d’Orléans, ¡Bourges, ¡France. ¡
9-‑11 ¡June ¡2015
SLIDE 2
Outline
n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions
2
SLIDE 3
Monitoring for Healthcare
3
SLIDE 4
Smart Homes
4
SLIDE 5 Motivations
n Smart home sensors + Robust data fusion
= Indoor location tracking,
= Activity Dailing Living characterization.
- n Indoor location tracking
= set-membership state reconstruction n Robust to sensor failures
5
SLIDE 6
Outline
n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions
6
SLIDE 7 Classical Estimation
n Classical estimation is probabilistic
f(p)
n ys
Optimisation of J(e(p))
e(p) ys p1 p2
Confidence sets
Yield valid results only if Perturbations, errors and model uncertainties with statistical properties known a priori Model structure is correct, no modeling errors
7
SLIDE 8 Set Membership Estimation
n Unknown but bounded-error framework
f(p)
n
Set membersip algorithm Y
p1 p2
Solution set Y
Hypothesis Uncertainties and errors are bounded with known prior bounds A set of feasible solutions S = {p ∈ P|f(p) ∈ Y} = f−1(Y) ∩ P
Set Membership Algorithm
8
SLIDE 9 n State estimation with continuous systems
l Prediction - Correction / Filtering approaches
- (Kieffer, et al., 1999) …
9
Set Membership Estimation
SLIDE 10
10
Set Membership Estimation
n Set inversion. Parameter estimation
l Branch-&-bound, branch-&-prune, interval contractors …
(Jaulin, et al. 93) (Raïssi et al., 2004)
SLIDE 11
Outline
n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions
11
SLIDE 12
Binary sensors
12
SLIDE 13
Binary sensors
13
SLIDE 14
14
SLIDE 15
System modeling
15
SLIDE 16
Predictor-Corrector Approach
16
Prediction step Correction step
SLIDE 17
Prediction step : random walk
17
SLIDE 18
Prediction step,
no motion detected
18
SLIDE 19
Use of RFID sensors
19
SLIDE 20
Correction step
20
SLIDE 21
q-Relaxed intersection
21
SLIDE 22
q-Relaxed intersection
(Jaulin, 2009)
22
SLIDE 23
q-Relaxed intersection
(Jaulin, 2009)
22
SLIDE 24
q-Relaxed intersection
(Jaulin, 2009)
22
SLIDE 25
q-Relaxed intersection
(Jaulin, 2009)
22
SLIDE 26
Outline
n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions
23
SLIDE 27
Location Tracking using
binary sensors only
24
SLIDE 28
Location Tracking using
binary sensors + RFID RSSI
25
SLIDE 29
Location tracking of
single inhabitant (IEEE ICRA 2015)
26
SLIDE 30
Location tracking of
single inhabitant (IEEE ICRA 2015)
26
SLIDE 31
Location tracking of
two inhabitants (IEEE CASE 2015)
27
SLIDE 32
Location tracking of
two inhabitants (IEEE CASE 2015)
27
SLIDE 33
Outline
n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions
28
SLIDE 34 29
Research directions
n Use forward-backward predictions n Extend to multiple inhabitants n Use with multi-modality n Apply to FDI (IFAC SafeProcess 2015)
- n Combine set-membership and stochastic
modeling of errors.
SLIDE 35 30
Focused References
n M.H. Amri, Y. Becis, D. Aubry, N. Ramdani, M. Fränzle,
Robust Indoor Location Tracking of Multiple Inhabitants Using Only Binary Sensors.
IEEE CASE 2015, Gothenburg, Accepted. n M.H. Amri, D. Aubry, Y. Becis, N. Ramdani,
Robust Fault Detection and Isolation applied to Indoor Localization.
IFAC SafeProcess 2015, Paris, Accepted. n M.H. Amri, D. Aubry, Y. Becis,
- N. Ramdani, Indoor Human/Robot Localization using Robust Multi-modal Data Fusion,
IEEE ICRA 2015. Accepted.
