Abstract
This article describes a connectionist vision system for the precise control of a robot designed to walk on the exterior of the space station. The network learns to use video camera input to determine the displacement of the robot's gripper relative to a hole in which the gripper must be inserted. Once trained, the network's output is used to control the robot, with a resulting factor of five fewer missed gripper insertions than occur when the robot walks without sensor feedback. The neural network visual feedback techniques described could also be applied in domains such as manufacturing, where precise robot positioning is required in an uncertain environment.
Article PDF
Similar content being viewed by others
References
Brown, H.B., Friedman, M.B., & Kanade, T. (1990). Development of a 5-DOF walking robot for space station application. Proceedings of the IEEE International Conference on Systems Engineering (pp. 194–197). Pittsburgh, PA: IEEE Press.
Davis, I., & Stentz, T. (1992). Personal communications.
Hampshire, J.B., & Waibel, A.H. (1989). The Meta-Pi network: building distributed knowledge representations for robust pattern recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14 (7), 751–769.
Jacobs, R.A., Jordan, M.I., & Barto, A.G. (1991). Task decomposition through competition in a modular connectionist architecture: the what and where vision tasks. Cognitive Science, 15 (2), 219–250.
Kohonen, T. (1990). Self-organization and associative memory, 3rd. ed. Berlin: Springer-Verlag.
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., & Jackel, L.D. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1 (4), 541–551.
MacQueen, J. (1967). Some methods of classification and analysis of multivariate observations. In L.M. LeCam & J. Neyman (Eds.), Proceedings of the 5th Berkeley Symposium on Mathematics, Statistics, and Probability. University of California Press, Berkeley, CA.
Poggio, T., & Girosi, F. (1990). Regularization algorithms for learning that are equivalent to multilayer networks. Science, 247, 987–982.
Pomerleau, D.A. (1991a). Efficient training of artificial neural networks for autonomous navigation. Neural Computation, 3 (1), 88–97.
Pomerleau, D.A. (1991b). Neural network-based vision processing for autonomous robot guidance. Proceedings of SPIE Conference on Aerospace Sensing (pp. 121–128). Orlando, FL.
Pomerleau, D.A. (1992). Neural network perception for mobile robot guidance. Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, PA. Also Technical Report CMU-CS-92-115.
Pomerleau, D.A. (1993). Neural network perception for mobile robot guidance. Norwell, MA: Kluwer Academic Publishers.
Rumelhart, D.E., Hinton, G.E., & Williams, R.J. (1986). Learning internal representations by error propagation. In D.E. Rumelhart & J.L. McClelland (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition. Vol. I: Foundations (pp. 318–362). Cambridge, MA: Bradford Books/MIT Press.
Ueno, H., Xu, Y., & Brown, H.B. (1990). On control and planning of a space station robot walker. In Proceedings of 1990 IEEE International Conference on Systems Engineering (pp. 220–223). Pittsburgh, PA: IEEE Press.
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech and Signal Processing, 37 (3), 328–339.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pomerleau, D.A. Neural Network-Based Vision for Precise Control of a Walking Robot. Machine Learning 15, 125–135 (1994). https://doi.org/10.1023/A:1022617321232
Issue Date:
DOI: https://doi.org/10.1023/A:1022617321232