Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection

Nikhil Das, Naman Gupta, Michael Yip
Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:496-504, 2017.

Abstract

We introduce the Fastron, a configuration space (C-space) model to be used as a proxy to kinematic-based collision detection. The Fastron allows iterative updates to account for a changing environment through a combination of a novel formulation of the kernel perceptron learning algorithm and an active learning strategy. Our simulations on a 7 degree-of-freedom arm indicate that proxy collision checks may be performed at least 2 times faster than an efficient polyhedral collision checker and at least 8 times faster than an efficient high-precision collision checker. The Fastron model provides conservative collision status predictions by padding C-space obstacles, and proxy collision checking time does not scale poorly as the number of workspace obstacles increases. All results were achieved without GPU acceleration or parallel computing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v78-das17a, title = {Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection}, author = {Das, Nikhil and Gupta, Naman and Yip, Michael}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {496--504}, year = {2017}, editor = {Levine, Sergey and Vanhoucke, Vincent and Goldberg, Ken}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/das17a/das17a.pdf}, url = {https://proceedings.mlr.press/v78/das17a.html}, abstract = {We introduce the Fastron, a configuration space (C-space) model to be used as a proxy to kinematic-based collision detection. The Fastron allows iterative updates to account for a changing environment through a combination of a novel formulation of the kernel perceptron learning algorithm and an active learning strategy. Our simulations on a 7 degree-of-freedom arm indicate that proxy collision checks may be performed at least 2 times faster than an efficient polyhedral collision checker and at least 8 times faster than an efficient high-precision collision checker. The Fastron model provides conservative collision status predictions by padding C-space obstacles, and proxy collision checking time does not scale poorly as the number of workspace obstacles increases. All results were achieved without GPU acceleration or parallel computing.} }
Endnote
%0 Conference Paper %T Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection %A Nikhil Das %A Naman Gupta %A Michael Yip %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-das17a %I PMLR %P 496--504 %U https://proceedings.mlr.press/v78/das17a.html %V 78 %X We introduce the Fastron, a configuration space (C-space) model to be used as a proxy to kinematic-based collision detection. The Fastron allows iterative updates to account for a changing environment through a combination of a novel formulation of the kernel perceptron learning algorithm and an active learning strategy. Our simulations on a 7 degree-of-freedom arm indicate that proxy collision checks may be performed at least 2 times faster than an efficient polyhedral collision checker and at least 8 times faster than an efficient high-precision collision checker. The Fastron model provides conservative collision status predictions by padding C-space obstacles, and proxy collision checking time does not scale poorly as the number of workspace obstacles increases. All results were achieved without GPU acceleration or parallel computing.
APA
Das, N., Gupta, N. & Yip, M.. (2017). Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection. Proceedings of the 1st Annual Conference on Robot Learning, in Proceedings of Machine Learning Research 78:496-504 Available from https://proceedings.mlr.press/v78/das17a.html.

Related Material