The unscented particle filter
In this paper, we propose a new particle filter based on sequential importance sampling. The algorithm uses a bank of unscented filters to obtain the importance proposal distribution. This proposal has two very "nice" properties. Firstly, it makes efficient use of the latest available info...
| मुख्य लेखकों: | , , , |
|---|---|
| स्वरूप: | Conference item |
| प्रकाशित: |
Neural information processing systems foundation
2001
|
| _version_ | 1826289641598222336 |
|---|---|
| author | Van Der Merwe, R Doucet, A De Freitas, N Wan, E |
| author_facet | Van Der Merwe, R Doucet, A De Freitas, N Wan, E |
| author_sort | Van Der Merwe, R |
| collection | OXFORD |
| description | In this paper, we propose a new particle filter based on sequential importance sampling. The algorithm uses a bank of unscented filters to obtain the importance proposal distribution. This proposal has two very "nice" properties. Firstly, it makes efficient use of the latest available information and, secondly, it can have heavy tails. As a result, we find that the algorithm outperforms standard particle filtering and other nonlinear filtering methods very substantially. This experimental finding is in agreement with the theoretical convergence proof for the algorithm. The algorithm also includes resampling and (possibly) Markov chain Monte Carlo (MCMC) steps. |
| first_indexed | 2024-03-07T02:31:59Z |
| format | Conference item |
| id | oxford-uuid:a78bd23c-b83c-40b1-adb3-aab6aa479ee9 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T02:31:59Z |
| publishDate | 2001 |
| publisher | Neural information processing systems foundation |
| record_format | dspace |
| spelling | oxford-uuid:a78bd23c-b83c-40b1-adb3-aab6aa479ee92022-03-27T02:55:21ZThe unscented particle filterConference itemhttp://purl.org/coar/resource_type/c_5794uuid:a78bd23c-b83c-40b1-adb3-aab6aa479ee9Symplectic Elements at OxfordNeural information processing systems foundation2001Van Der Merwe, RDoucet, ADe Freitas, NWan, EIn this paper, we propose a new particle filter based on sequential importance sampling. The algorithm uses a bank of unscented filters to obtain the importance proposal distribution. This proposal has two very "nice" properties. Firstly, it makes efficient use of the latest available information and, secondly, it can have heavy tails. As a result, we find that the algorithm outperforms standard particle filtering and other nonlinear filtering methods very substantially. This experimental finding is in agreement with the theoretical convergence proof for the algorithm. The algorithm also includes resampling and (possibly) Markov chain Monte Carlo (MCMC) steps. |
| spellingShingle | Van Der Merwe, R Doucet, A De Freitas, N Wan, E The unscented particle filter |
| title | The unscented particle filter |
| title_full | The unscented particle filter |
| title_fullStr | The unscented particle filter |
| title_full_unstemmed | The unscented particle filter |
| title_short | The unscented particle filter |
| title_sort | unscented particle filter |
| work_keys_str_mv | AT vandermerwer theunscentedparticlefilter AT douceta theunscentedparticlefilter AT defreitasn theunscentedparticlefilter AT wane theunscentedparticlefilter AT vandermerwer unscentedparticlefilter AT douceta unscentedparticlefilter AT defreitasn unscentedparticlefilter AT wane unscentedparticlefilter |