Fuzzy Clustering of Human Locomotor Motion

There have been a number o f attempts to overcome some o f the shortcomings of “teaching by guiding” approach. Summers and Grossman1-21 embedded a collection of the sensory information and interaction with the operator in the task instruction procedure. Asada and Assari131 used neural networks to extract the control rules to perform a particular assembly motion from the position and force data generated during operation of a human operator. Due to unintentional and inconsistent motion commands generated by the operator during demonstration, direct training has proved difficult. Sator and Hirai141 integrated direct teaching with task level languages through master-slave manipulators.