1 / 24

CSE-473 Project 2 Monte Carlo Localization

CSE-473 Project 2 Monte Carlo Localization. Localization as state estimation. Motion: Perception: … is optimal under the Markov assumption. Kalman filters, Hidden Markov Models, DBN. Markov Localization as State Estimation (2). Markov!. Markov!. Kalman Filters.

chin
Download Presentation

CSE-473 Project 2 Monte Carlo Localization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CSE-473 Project 2 Monte Carlo Localization

  2. Localization as state estimation

  3. Motion: Perception:… is optimal under the Markov assumption Kalman filters, Hidden Markov Models, DBN Markov Localization as State Estimation (2) Markov! Markov!

  4. Kalman Filters [Schiele et al. 94], [Weiß et al. 94], [Borenstein 96], [Gutmann et al. 96, 98], [Arras 98]

  5. Piecewise constant [Burgard et al. 96,98], [Fox et al. 99], [Konolige et al. 99]

  6. Particle Filters • Represent density by random samples • Estimation of non-Gaussian, nonlinear processes • Monte Carlo filter, Survival of the fittest, Condensation, Bootstrap filter, Particle filter • Filtering: [Handschin, 70], [Gordon et al., 93], [Kitagawa 96] • Computer vision: [Isard et al. 96, 98] • DBN: [Kanazawa et al., 95]

  7. Sample-based Density Representation • Converges to true density

  8. Importance Sampling Weight samples:

  9. Sample-based Density Representation

  10. Sensor Information: Importance Sampling

  11. Robot Motion

  12. Sensor Information: Importance Sampling

  13. Robot Motion

  14. Monte Carlo Localization (SIR) • Set of samples St = {<l1, p1>, … <lN, pN>} described by position land weight p • Initialize sample set S0according to prior knowledge • For each motion D do: • Sampling: Generate from each sample in St-1 a new sample according to motion model • For each observation s do: • Importance sampling: Re-weight each sample with the likelihood • Resampling: Draw N samples from sample set St according to their likelihood

  15. Motion Model P(l | a, l’) Model odometry error as Gaussian noise on a, b, and d

  16. Motion Model P(l | a, l’) Start

  17. Global Localization (sonar)

  18. Using Ceiling Maps for Localization [Dellaert et al. 99]

  19. P(z|x) z h(x) Vision-based Localization

  20. Vision-based Localization [CVPR-99]

  21. Comparison to Grid-based Markov Localization (2) • Office environment: 20,000 samples versus 150 million states • NMAH: Global localization in 15 seconds instead of 4 minutes • Vision-based: Can track the position in situations in which grid-based approach fails

  22. Condensation Tracking

  23. Mixed-State Tracking

  24. Tracking Multiple People

More Related