Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
An implementation of a biped robot which as capable of dynamic walking by a simple nonlinear control algorithm. is presented. Four D.C. servo motors actuate the knee and ankle joi...
We introduce a multi-model variant of the EMT-based control algorithm. The new algorithm, MM-EMT, is capable of balancing several control tasks expressed using separate dynamic mo...
Zinovi Rabinovich, Nir Pochter, Jeffrey S. Rosensc...
We propose a novel method to estimate the object that a user is focusing on by using the synchronization between the movements of objects and a user's eyes as a cue. We first ...
The usefulness of a video database depends on whether the video of interest can be easily located. In this paper, we propose a video retrieval algorithm based on the integration o...