ML Anthology

Efficient Training of Artificial Neural Networks for Autonomous Navigation

Dean Pomerleau
NeCo 1991 pp. 88-97
doi:10.1162/NECO.1991.3.1.88 /neco/1991/pomerleau1991neco-efficient/

Abstract

The ALVINN (Autonomous Land Vehicle In a Neural Network) project addresses the problem of training artificial neural networks in real time to perform difficult perception tasks. ALVINN is a backpropagation network designed to drive the CMU Navlab, a modified Chevy van. This paper describes the training techniques that allow ALVINN to learn in under 5 minutes to autonomously control the Navlab by watching the reactions of a human driver. Using these techniques, ALVINN has been trained to drive in a variety of circumstances including single-lane paved and unpaved roads, and multilane lined and unlined roads, at speeds of up to 20 miles per hour.

PDF NeCo Semantic Scholar

Cite

Text

Pomerleau. "Efficient Training of Artificial Neural Networks for Autonomous Navigation." Neural Computation, 1991. doi:10.1162/NECO.1991.3.1.88

Markdown

[Pomerleau. "Efficient Training of Artificial Neural Networks for Autonomous Navigation." Neural Computation, 1991.](https://mlanthology.org/neco/1991/pomerleau1991neco-efficient/) doi:10.1162/NECO.1991.3.1.88

BibTeX

@article{pomerleau1991neco-efficient,
  title     = {{Efficient Training of Artificial Neural Networks for Autonomous Navigation}},
  author    = {Pomerleau, Dean},
  journal   = {Neural Computation},
  year      = {1991},
  pages     = {88-97},
  doi       = {10.1162/NECO.1991.3.1.88},
  volume    = {3},
  url       = {https://mlanthology.org/neco/1991/pomerleau1991neco-efficient/}
}