Dynamic Bayesian Approach to Estimation and Filtering during Contact Tasks
Event details
| Date | 17.06.2013 |
| Hour | 11:00 |
| Speaker | Jeff Trinkle, Rensselaer Polytechnic Institute, Troy, NY 12180 |
| Location |
ELA2
|
| Category | Conferences - Seminars |
In this work, we develop a solution to a broad class of grasping and manipulation problems that we term as C-SLAM for "contact simultaneous localization and modeling," in which robots need to accurately track the motions of the contacted bodies and the locations of contacts while simultaneously estimating important system parameters, such as body dimensions, masses and friction coefficients. Our solution is based on a dynamic Bayesian inference framework, and hence, we refer to it as Dynamic Bayesian C-SLAM (DBC-SLAM). DBC-SLAM combines a model of multibody dyanmics with a dynamic Bayesian network, and incorporates model parameter estimation as an intrinsic part of the overall inference procedure. We show two preliminary proof-of-concept examples that demonstrate the use of DBC-SLAM in robotic contact tasks.
Practical information
- General public
- Free
Organizer
- LASA
Contact
- Mayra LIROT