The need for knowing future manipulator motion arises in several robotics applications, including notification or avoidance of imminent collisions and real-time optimization of velocity commands. This paper presents a real-time, low overhead algorithm for identification of future manipulator motions, based on measurements of prior motions and the instantaneous sensed actuator velocity commanded by an operator. Experimental results with a human-controlled, two degree-of-freedom manipulator demonstrate the ability to quickly learn and accurately estimate future manipulator motions.

This paper describes a novel auto-calibration state-trajectory-based control method and its application to electronic flow control for independent metering systems. In this paper, the independent metering architecture that is considered uses five Electro-Hydraulic Poppet Valves (EHPV's). The proposed control method is applied to four of these valves, arranged in a Wheatstone bridge configuration, to regulate the flow of hydraulic oil coming into and out of an actuator. For simplicity, the fifth valve is operated via open-loop to control the supply pressure. Experimental data presented herein demonstrate that the control method learns the valve's conductance characteristics (i.e. the inverse input-state dynamic map of the valve) while simultaneously controlling the motion of the hydraulic actuator.