- Abstract:
-
We consider the problem of tactile discrimination, with the goal of estimating an underlying state parameter in a sequential setting. If the data is continuous and high-dimensional, collecting enough representative data samples becomes difficult. We present a framework that uses active learning to help with the sequential gathering of data samples, using information-theoretic criteria to find optimal actions at each time step. We consider two approaches to recursively update the state parameter belief: an analytical Gaussian approximation and a Monte Carlo sampling method. We show how both active frameworks improve convergence, demonstrating results on a real robotic hand-arm system that estimates the viscosity of liquids from tactile feedback data.
- Links To Paper
- Published version
- Bibtex format
- @InProceedings{EDI-INF-RR-1370,
- author = {
Hannes Saal
and Jo-Anne Ting
and Sethu Vijayakumar
},
- title = {Active sequential learning with tactile feedback},
- book title = {Proc. 13th Int. Conf. on Artificial Intelligence and Statistics (AISTATS) 2010, JMLR: W&CP},
- publisher = {JMLR},
- year = 2010,
- month = {May},
- volume = {9},
- pages = {677-684},
- url = {http://jmlr.csail.mit.edu/proceedings/papers/v9/saal10a/saal10a.pdf},
- }
|
