Mark Karpenko

Learn More
In this paper, reinforcement learning is applied to coordinate, in a decentralized fashion, the motions of a pair of hydraulic actuators whose task is to firmly hold and move an object along a specified trajectory under conventional position control. The learning goal is to reduce the interaction forces acting on the object that arise due to inevitable(More)
— This paper documents the development and experimental evaluation of a practical nonlinear position controller for a typical industrial pneumatic actuator that gives good performance for both regulating and reference tracking tasks. The system is comprised of a low-cost 5-port proportional valve with flow deadband and a double-rod actuator exhibiting(More)
— Quantitative feedback theory (QFT) is applied towards the design of a simple and effective position controller for a typical low-cost industrial pneumatic actuator with a 5-port three-way control valve, that is subject to disturbing forces. A simple fixed-gain proportional-integral control law with dynamic pressure feedback is synthesized to guarantee the(More)
— This paper presents a pseudospectral (PS) optimal control algorithm for the autonomous motion planning of a fleet of unmanned ground vehicles (UGVs). The UGVs must traverse an obstacle-cluttered environment while maintaining robustness against possible collisions. The generality of the algorithm comes from a binary logic that modifies the cost function(More)
The tip-of-the-tongue state, or memory blocking, has been investigated from the point of view of possibilities of its neural network modeling. The results of neuropsychological and neurobiological studies on memory blocking have been reviewed, and basic problems whose solution could contribute to the comprehension of this phenomenon have been formulated.(More)