Biologically Inspired Online Learning of Visual Autonomous Driving
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.94
Abstract
While autonomously driving systems accumulate more and more sensors as well as highly specialized visual features and engineered solutions, the human visual system provides evidence that visual input and simple low level image features are sufficient for successful driving. In this paper we propose extensions (non-linear update and coherence weighting) to one of the simplest biologically inspired learning schemes (Hebbian learning). We show that this is sufficient for online learning of visual autonomous driving, where the system learns to directly map low level image features to control signals. After the initial training period, the system seamlessly continues autonomously. This extended Hebbian algorithm, qHebb, has constant bounds on time and memory complexity for training and evaluation, independent of the number of training samples presented to the system. Further, the proposed algorithm compares favorably to state of the art engineered batch learning algorithms.
Session
Poster Session
Files
Extended Abstract (PDF, 1 page, 328K)Paper (PDF, 12 pages, 824K)
Supplemental Materials (ZIP, 8.9M)
Bibtex File
Citation
Kristoffer Öfjäll, and Michael Felsberg. Biologically Inspired Online Learning of Visual Autonomous Driving. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.94
title = {Biologically Inspired Online Learning of Visual Autonomous Driving},
author = {Öfjäll, Kristoffer and Felsberg, Michael},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.94 }
}