Perception of Non-Rigid Motion: Inference of Shape, Material and Force
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Vision and Robotics. Pages 1565-1569.
Abstract
Most non-rigid motion is much simpler than is generally thought, having many fewer degrees of freedom than, for instance, 3-D shape . The relatively circumscribed nature of nonrigid motion can be seen by examining it from the perspective of vibration modes. The fact that a small number of parameters are sufficient to describe non-rigid motion mean that it is plausible to use sensory data to recover a nearly complete physical model of an object, so that we can, for instance, predict its response to impinging forces. One perceptual task of considerable interest is estimating material properties such as stiffness, strength, and mass by watching, touching or listening to collisions. We derive equations which allow estimates of these material properties to be extracted from visual and tactile data, and speculate on the use of aural data.
@inproceedings{ijcai1989p249,
title = {Perception of Non-Rigid Motion: Inference of Shape, Material and Force},
author = {Pentland, Alex and Williams, John},
booktitle = {Proceedings of the Eleventh International Joint Conference on
Artificial Intelligence, {IJCAI-89}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {N. S. Sridharan},
pages = {1565--1569},
year = {1989},
month = {8},
note = {Vision and Robotics},
url = {https://ijcai.org/proceedings/1989/249},
}
TY - CPAPER TI - Perception of Non-Rigid Motion: Inference of Shape, Material and Force AU - Pentland, Alex AU - Williams, John T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 1565 EP - 1569 UR - https://ijcai.org/proceedings/1989/249 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
