Event
Stochastic Information Processing [WS2124113]
Type
lecture (V)Präsenz/Online gemischt
Term
WS 21/22SWS
3Language
DeutschAppointments
29Organisation
- KIT-Fakultät für Informatik
Part of
Literature
Weiterführende Literatur
Skript zur Vorlesung
Appointments
- 21.10.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 27.10.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 28.10.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 03.11.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 04.11.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 10.11.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 11.11.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 17.11.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 18.11.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 24.11.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 25.11.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 01.12.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 02.12.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 08.12.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 09.12.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 15.12.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 16.12.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 22.12.2021 16:00 - 17:30 - Room: 50.20 Raum 148
- 23.12.2021 14:00 - 15:30 - Room: 50.34 Raum -102
- 12.01.2022 16:00 - 17:30 - Room: 50.20 Raum 148
- 13.01.2022 14:00 - 15:30 - Room: 50.34 Raum -102
- 19.01.2022 16:00 - 17:30 - Room: 50.20 Raum 148
- 20.01.2022 14:00 - 15:30 - Room: 50.34 Raum -102
- 26.01.2022 16:00 - 17:30 - Room: 50.20 Raum 148
- 27.01.2022 14:00 - 15:30 - Room: 50.34 Raum -102
- 02.02.2022 16:00 - 17:30 - Room: 50.20 Raum 148
- 03.02.2022 14:00 - 15:30 - Room: 50.34 Raum -102
- 09.02.2022 16:00 - 17:30 - Room: 50.20 Raum 148
- 10.02.2022 14:00 - 15:30 - Room: 50.34 Raum -102
Note
In order to handle complex dynamic systems (e.g., in robotics), an in-step estimation of the system's internal state (e.g., position and orientation of the actuator) is required. Such an estimation is ideally based on the system model (e.g., a discretized differential equation describing the system dynamics) and the measurement model (e.g., a nonlinear function that maps the state space to a measurement subspace). Both system and measurement model are uncertain (e.g., include additive or multiplicative noise).
For continuous state spaces, an exact calculation of the probability densities is only possible in a few special cases. In practice, general nonlinear systems are often traced back to these special cases by simplifying assumptions. One extreme is linearization with subsequent application of linear estimation theory. However, this often leads to unsatisfactory results and requires additional heuristic measures. At the other extreme are numerical approximation methods, which only evaluate the desired distribution densities at discrete points in the state space. Although the working principle of these procedures is usually quite simple, a practical implementation often turns out to be difficult and especially for higher-dimensional systems it is computationally complex.
As a middle ground, analytical nonlinear estimation methods would therefore often be desirable. In this lecture the main difficulties in the development of such estimation methods are presented and corresponding solution modules are presented. Based on these building blocks, some analytical estimation methods are discussed in detail as examples, which are very suitable for practical implementation and offer a good compromise between computing effort and performance. Useful applications of these estimation methods are also discussed. Both known methods and the results of current research are presented.