Timeline for Unscented Kalman Filter VS Extended Kalman Filter on stability
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 19 at 0:25 | comment | added | euraad | @TimWescott Wow, old question. But I have found the real answer. A UKF will perform much better than a linear KF or linerarized KF, due to the uncented form. | |
| Nov 18 at 16:02 | comment | added | TimWescott | If one was clearly always better than another, there would only be that one kind, and the rest would only be found in footnotes and unread papers. Which one is better depends on your problem at hand. So your question should be "How do I decide whether to use a linear Kalman, EKF, or UKF?" (Or a particle filter or other general Baysian state estimator). | |
| Oct 19, 2017 at 17:56 | comment | added | euraad | So EKF is not stable? | |
| Oct 19, 2017 at 11:30 | comment | added | daaxix | Kalman filters are not controls, they are observer estimations, i.e. they improve the accuracy of your model state estimate. They are only suited for certain system types, particularly linear systems with Gaussian noise in the sensors. You may need to adjust your control strategy instead of your observer strategy to achieve stability. | |
| Oct 14, 2017 at 7:10 | vote | accept | euraad | ||
| Oct 13, 2017 at 21:07 | answer | added | Vignesh | timeline score: 2 | |
| Oct 9, 2017 at 20:32 | comment | added | euraad | I don't know. @chuck | |
| Oct 9, 2017 at 18:57 | comment | added | Chuck♦ | How are you discretizing the system? | |
| Oct 9, 2017 at 7:13 | history | asked | euraad | CC BY-SA 3.0 |