Robust indoor loca/on tracking via interval analysis

Transcription

1 Robust indoor loca/on tracking via interval analysis Mohamed- Hédi AMRI, Yasmina BECIS, Didier AUBRY & Nacim RAMDANI Université d Orléans, Bourges, France.!! SWIM 2015, Praha 9-11 June 2015

2 2 Outline n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions

3 Monitoring for Healthcare 3

4 4 Smart Homes

5 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

6 6 Outline n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions

7 Nacim Ramdani et al. Set-membership identification... 7 Classical Estimation n Classical estimation is probabilistic y s p 1 Confidence sets y s f(p) e(p) Optimisation of J(e(p)) n p 2 Yield valid results only if Y p 1 Perturbations, errors and model uncertainties Méthode ensembliste with statistical f(p) properties known apriori n Y Model structure is correct, no modeling errors Ensemble solution p 2

8 y s p 1 s Set e(p) Membership Estimation Optimisation de J(e(p)) n Unknown but bounded-error framework Y p 1 Y Set Set Membership membersip algorithm Algorithm f(p) Solution set p 2 n p 2 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 Nacim Ramdani et al. Set-membership identification... 8

9 9 Set Membership Estimation n State estimation with continuous systems l Prediction - Correction / Filtering approaches (Kieffer, et al., 1999)

10 Set Membership Estimation n Set inversion. Parameter estimation l Branch-&-bound, branch-&-prune, interval contractors (Jaulin, et al. 93) (Raïssi et al., 2004) 10

11 11 Outline n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions

12 12 Binary sensors

13 13 Binary sensors

14 14

15 15 System modeling

16 16 Predictor-Corrector Approach Prediction step Correction step

17 Prediction step : random walk 17

18 Prediction step, no motion detected 18

19 19 Use of RFID sensors

20 20 Correction step

21 q-relaxed intersection 21

22 q-relaxed intersection (Jaulin, 2009) 22

23 q-relaxed intersection (Jaulin, 2009) 22

24 q-relaxed intersection (Jaulin, 2009) 22

25 q-relaxed intersection (Jaulin, 2009) 22

26 23 Outline n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions

27 Location Tracking using binary sensors only 24

28 Location Tracking using binary sensors + RFID RSSI 25

29 Location tracking of single inhabitant (IEEE ICRA 2015) 26

30 Location tracking of single inhabitant (IEEE ICRA 2015) 26

31 Location tracking of two inhabitants (IEEE CASE 2015) 27

32 Location tracking of two inhabitants (IEEE CASE 2015) 27

33 28 Outline n Motivations n Set membership estimation n Indoor location tracking n Experimental evaluation n Research directions

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.

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 Accepted.