Recognizing teleoperated manipulations

The many degrees-of-freedom and distributed sensing capability of dextrous robot hands permit the use of control programs that rely on qualitative changes in sensor feedback. One way of designing such a control program is to have the robot learn the qualitative control characteristics from examples. These examples may be provided via teleoperation. Results are presented for recognizing and segmenting manipulation primitives from a teleoperated task by analysis of features in sensor feedback. k-nearest quantized pattern vectors determine potential classifications. A hidden Markov model provides task context for the final segmentation. The illustrative task is picking up a plastic egg with a spatula.<<ETX>>

[1]  M. Bornstein,et al.  Development in Infancy , 1982 .

[2]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[3]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[4]  Blake Hannaford,et al.  Hidden Markov Model Analysis of Force/ Torque Information in Telemanipulation , 1989, ISER.

[5]  Teuvo Kohonen,et al.  Improved versions of learning vector quantization , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[6]  Peter K. Allen,et al.  Mapping haptic exploratory procedures to multiple shape representations , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[7]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[8]  Ruzena Bajcsy,et al.  Sensorimotor Learning Using Active Perception in Continuous Domains , 1991 .

[9]  Dana H. Ballard,et al.  Principles of animate vision , 1992, CVGIP Image Underst..

[10]  Dana H. Ballard,et al.  Sensing qualitative events to control manipulation , 1992, Other Conferences.