Skip to main content
Article
Sensorimotor Primitives for Robotic Assembly Skills
Institute for Software Research
  • J. Dan Morrow, Carnegie Mellon University
  • Pradeep Khosla, Carnegie Mellon University
Date of Original Version
1-1-1995
Type
Conference Proceeding
Abstract or Description

Many researchers are interested in developing robust, skill-achieving robot programs. We propose the development of asensorimotor primitive layer which bridges the gap between the robot/sensor system and a class of tasks by providing useful encapsulations of sensing and action. Skills can then be constructed from this library of sensor-driven primitives. This reflects a move away from the separation of sensing and action in robot programming of task strategies towards the integration of sensing and action in a domain-general way for broad classes of tasks. For the domain of rigid-body assembly, we are exploiting the motion constraints which define assembly to develop force sensor-driven primitives. We report on the experimental results of a D-connector insertion skill implemented using several force-driven primitives.

Citation Information
J. Dan Morrow and Pradeep Khosla. "Sensorimotor Primitives for Robotic Assembly Skills" (1995)
Available at: http://works.bepress.com/pradeep_khosla/120/