Skip to content
Back to outputs

Predicting terrain contours using a feed-forward neural network

Research output: Contribution to journalArticle

Standard

Predicting terrain contours using a feed-forward neural network. / Erwin-Wright, Stephen; Sanders, David; Chen, Sheng.

In: Engineering Applications of Artificial Intelligence, Vol. 16, No. 5-6, 2003, p. 465-472 .

Research output: Contribution to journalArticle

Harvard

Erwin-Wright, S, Sanders, D & Chen, S 2003, 'Predicting terrain contours using a feed-forward neural network', Engineering Applications of Artificial Intelligence, vol. 16, no. 5-6, pp. 465-472 . https://doi.org/10.1016/j.engappai.2003.08.002

APA

Erwin-Wright, S., Sanders, D., & Chen, S. (2003). Predicting terrain contours using a feed-forward neural network. Engineering Applications of Artificial Intelligence, 16(5-6), 465-472 . https://doi.org/10.1016/j.engappai.2003.08.002

Vancouver

Erwin-Wright S, Sanders D, Chen S. Predicting terrain contours using a feed-forward neural network. Engineering Applications of Artificial Intelligence. 2003;16(5-6):465-472 . https://doi.org/10.1016/j.engappai.2003.08.002

Author

Erwin-Wright, Stephen ; Sanders, David ; Chen, Sheng. / Predicting terrain contours using a feed-forward neural network. In: Engineering Applications of Artificial Intelligence. 2003 ; Vol. 16, No. 5-6. pp. 465-472 .

Bibtex

@article{f070106f06d142e9bb8f35977bbc7475,
title = "Predicting terrain contours using a feed-forward neural network",
abstract = "Wheeled or tracked vehicles cannot move easily over much of the land surface of the earth. This paper describes research work to create walking machines that are able to travel when the terrain makes wheeled or tracked vehicles ineffective. These legged walking vehicles must be able to negotiate unknown environments with little or no knowledge of the terrain. A predictive terrain contour mapping strategy is proposed that uses a feed-forward neural network trained using a back-propagation algorithm to predict contours based on leg positions and orientations. The strategy is tested using the abilities of a tele-operated eight-legged robot named {\textquoteleft}{\textquoteleft}Robug IV{\textquoteright}{\textquoteright}. Predicted performance is an improvement on previous implementations and a summarised comparison of the results for the four terrains is provided.",
author = "Stephen Erwin-Wright and David Sanders and Sheng Chen",
year = "2003",
doi = "10.1016/j.engappai.2003.08.002",
language = "English",
volume = "16",
pages = "465--472 ",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",
number = "5-6",

}

RIS

TY - JOUR

T1 - Predicting terrain contours using a feed-forward neural network

AU - Erwin-Wright, Stephen

AU - Sanders, David

AU - Chen, Sheng

PY - 2003

Y1 - 2003

N2 - Wheeled or tracked vehicles cannot move easily over much of the land surface of the earth. This paper describes research work to create walking machines that are able to travel when the terrain makes wheeled or tracked vehicles ineffective. These legged walking vehicles must be able to negotiate unknown environments with little or no knowledge of the terrain. A predictive terrain contour mapping strategy is proposed that uses a feed-forward neural network trained using a back-propagation algorithm to predict contours based on leg positions and orientations. The strategy is tested using the abilities of a tele-operated eight-legged robot named ‘‘Robug IV’’. Predicted performance is an improvement on previous implementations and a summarised comparison of the results for the four terrains is provided.

AB - Wheeled or tracked vehicles cannot move easily over much of the land surface of the earth. This paper describes research work to create walking machines that are able to travel when the terrain makes wheeled or tracked vehicles ineffective. These legged walking vehicles must be able to negotiate unknown environments with little or no knowledge of the terrain. A predictive terrain contour mapping strategy is proposed that uses a feed-forward neural network trained using a back-propagation algorithm to predict contours based on leg positions and orientations. The strategy is tested using the abilities of a tele-operated eight-legged robot named ‘‘Robug IV’’. Predicted performance is an improvement on previous implementations and a summarised comparison of the results for the four terrains is provided.

U2 - 10.1016/j.engappai.2003.08.002

DO - 10.1016/j.engappai.2003.08.002

M3 - Article

VL - 16

SP - 465

EP - 472

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 5-6

ER -

ID: 1767624