Abstract
The paper presents an original approach for visual identification of road direction of an autonomous vehicle using an improved Radial Basis Function (RBF) neural network. We present the results of designing, software implementation, training, and testing of our RBF model for automatic road direction detection as a function of the input image. The path to be identified was quantified in 5 output directions. For training and testing the neural model, we used two lots of real road scenes: 50 images for training and other 50 images for test. The score of correct road recognition was of 100% both for estimation lot and also for the test lot. We have also designed a driving simulator to evaluate the performances of the neural road follower.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baluja, S.: Evolution of Artificial Neural Network Based Autonomous Land Vehicle Controller. IEEE Trans. Syst., Man, and Cybern. 3 (1996) 450–463
Del Bimbo, A., Landi, L., Santini, S.: Determination of Road Directions Using Feedback Neural Nets. Signal Processing. 1–2 (1993) 147–160.
Kuan, D., Philipps, G., Hsueh, A.-C. Autonomous Robotic Vehicle Road Following. IEEE Trans. Part. Anal. Mach. Intell. 5 (1988) 648–658
Neagoe, V.: Intelligent Detection of FSK Signals Using a Refined Radial Basis Function. In: Fazekas, K. (ed.): Intelligent Terminals and Source and Channel Coding. HTE-Scientific Society for Communications, Budapest (1993) 201–209.
Neagoe, V., Lemahieu, I., Cristureanu, D., Hargalas, D., Constantinescu, B., Popescu, C.: A Parallel Image Processing for Optimum Direction Finding in Autonomous Vehicle Navigation. In: D’Hollander, E.H., Joubert, G. R., Peters, F. J., Trystam, T. (eds.): Parallel Computing: State of the Art and Perspectives. Advances in Parallel Computing, Vol. 11. Elsevier, Amsterdam New York Tokyo (1996). 681–684
Neagoe, V., Sabac, B.: A Connectionist Model For Road Identification in an Autonomous Vehicle Controller. In: Proceedings of the 27th International Conference of the Romanian Technical Military Academy. Section X. Technical Military Academy Publishing House, Bucharest (1997) 62–69
Pomerlau, D. A.: Efficient Training of Artificial Neural Networks for Autonomous Navigation. Neural Comp. 1 (1991) 88–97
Rosenblum, M., Davis, L. S.,: An Improved Radial Basis Function Network for Visual Autonomous Road Folowing. IEEE Trans. Neural Networks. 5 (1996) 1111–1120
Thorpe, C., Hebert, M.-H, Kanade, T., Shaffer S.-A: Vision and Navigation for the Carnegie-Mellon NAVLAB”, IEEE Trans. Part. Anal. Mach. Mell. 3 (1988) 362–273
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neagoe, V., Valcu, M., Sabac, B. (1999). A Neural Approach for Detection of Road Direction in Autonomous Navigation. In: Reusch, B. (eds) Computational Intelligence. Fuzzy Days 1999. Lecture Notes in Computer Science, vol 1625. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48774-3_38
Download citation
DOI: https://doi.org/10.1007/3-540-48774-3_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66050-7
Online ISBN: 978-3-540-48774-6
eBook Packages: Springer Book Archive