منابع مشابه
Vision-Based Robot Learning for Behavior Acquisition
We introduce our approach, a new direction of robotics research that makes a robot learn to behave adequately to accomplish a given task at hand through the interactions with its environment with less a priori knowledge about the environment or the robot itself. We brie y present three research topics of vision-based robot learning in each of which visual perception is tightly coupled with actu...
متن کاملBehavior Acquisition via Vision-Based Robot Learning
We introduce our approach that makes a robot learn to behave adequately to accomplish a given task at hand through the interactions with its environment with less a priori knowledge about the environment or the robot itself. We briefly present three research topics of vision-based robot learning in each of which visual perception is tightly coupled with actuator effects so as to learn an adequa...
متن کاملVision-Based Reinforcement Learning for Purposive Behavior Acquisition
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement learning method to a real robot with vision sensor. First, a \state-action deviation" problem is found as a form of perceptual aliasing in constructing the state and action spaces that re ect the outputs from physical...
متن کاملContinuous Valued Q-learning for Vision-Guided Behavior Acquisition
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 real robot tasks because of poor performance of learned behavior and further a new problem of state space construction. This paper proposes a continuous valued Q-learning for real robot applications, which calculates co...
متن کاملPhase-Correlation Guided Search for Realtime Stereo Vision
In this paper, we propose a new theoretical framework, which is based on phase-correlation, for efficiently solving the correspondence problem. The proposed method allows area matching algorithms to perform at high frame rates, and can be applied to various problems in computer vision. In particular, we demonstrate the advantages of this method in the estimation of dense disparity maps in real ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the Robotics Society of Japan
سال: 1995
ISSN: 0289-1824,1884-7145
DOI: 10.7210/jrsj.13.351