Neural Networks for Tactile Perception
Abstract
Integrated tactile sensors appear to be essential for dextrous control of multifingered robotic hands. Such sensors would feature (1) compliant contact surfaces, (2) high resolution surface stress transduction, (3) local signal conditioning, and (4) local computation to recover contact surface stress. The last-mentioned item pertains to the basic inverse problem of tactile perception and the real time solution of this inverse problem is our primary concern. We think that good solutions to this problem (i.e. algorithms + implementations ) will be needed for realizing dextrous hand control via tactile servoing. In this paper we describe a processor chip designed to solve the mathematical inversion problem utilizing neural network principles. An energy function for the network is derived and we show that the equilibrium states are just regularized solutions to the inversion problem. Simulations indicate that this chip can function in the presence of large amounts of electrical noise. In addition the effect of processing induced variability in sensor response can also be minimized using the maximum entropy estimate method described below.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1987
- Accession Number
- ADA453206
Entities
People
- C. R. Marrian
- C. T. Yao
- Daniel J. Friedman
- M. C. Peckerar
- P.S.Krishnaprasad
- Rong Yang
- Y. C. Pati
Organizations
- University of Maryland