Institute Homepage DE Sign In

Back

Autonomous Motion Conference Paper 2000

Real Time Learning in Humanoids: A challenge for scalability of Online Algorithms

Thumb ticker sm ss
Autonomous Motion
Stefan Schaal
  • Director

While recent research in neural networks and statistical learning has focused mostly on learning from finite data sets without stringent constraints on computational efficiency, there is an increasing number of learning problems that require real-time performance from an essentially infinite stream of incrementally arriving data. This paper demonstrates how even high-dimensional learning problems of this kind can successfully be dealt with by techniques from nonparametric regression and locally weighted learning. As an example, we describe the application of one of the most advanced of such algorithms, Locally Weighted Projection Regression (LWPR), to the on-line learning of the inverse dynamics model of an actual seven degree-of-freedom anthropomorphic robot arm. LWPR's linear computational complexity in the number of input dimensions, its inherent mechanisms of local dimensionality reduction, and its sound learning rule based on incremental stochastic leave-one-out cross validation allows -- to our knowledge for the first time -- implementing inverse dynamics learning for such a complex robot with real-time performance. In our sample task, the robot acquires the local inverse dynamics model needed to trace a figure-8 in only 60 seconds of training.

Author(s): Vijayakumar, S. and Schaal, S.
Book Title: Humanoids2000, First IEEE-RAS International Conference on Humanoid Robots
Year: 2000
Month: September
Day: 6-7
Publisher: CD-Proceedings
Bibtex Type: Conference Paper (inproceedings)
Address: Cambridge, MA
URL: http://www-slab.usc.edu/publications/V/vijayakumar-ICHR2000.pdf
Cross Ref: p1424
Electronic Archiving: grant_archive
Note: clmc

BibTex 

@inproceedings{Vijayakumar_HFIICHR_2000,
  title = {Real Time Learning in Humanoids: A challenge for scalability of Online Algorithms},
  booktitle = {Humanoids2000, First IEEE-RAS International Conference on Humanoid Robots},
  abstract = {While recent research in neural networks and statistical learning has focused mostly on learning from finite data sets without stringent constraints on computational efficiency, there is an increasing number of learning problems that require real-time performance from an essentially infinite stream of incrementally arriving data. This paper demonstrates how even high-dimensional learning problems of this kind can successfully be dealt with by techniques from nonparametric regression and locally weighted learning. As an example, we describe the application of one of the most advanced of such algorithms, Locally Weighted Projection Regression (LWPR), to the on-line learning of the inverse dynamics model of an actual seven degree-of-freedom anthropomorphic robot arm. LWPR's linear computational complexity in the number of input dimensions, its inherent mechanisms of local dimensionality reduction, and its sound learning rule based on incremental stochastic leave-one-out cross validation allows -- to our knowledge for the first time -- implementing inverse dynamics learning for such a complex robot with real-time performance. In our sample task, the robot acquires the local inverse dynamics model needed to trace a figure-8 in only 60 seconds of training.},
  publisher = {CD-Proceedings},
  address = {Cambridge, MA},
  month = sep,
  year = {2000},
  note = {clmc},
  slug = {vijayakumar_hfiichr_2000},
  author = {Vijayakumar, S. and Schaal, S.},
  crossref = {p1424},
  url = {http://www-slab.usc.edu/publications/V/vijayakumar-ICHR2000.pdf},
  month_numeric = {9}
}