Transactions of the Society of Instrument and Control Engineers
Online ISSN : 1883-8189
Print ISSN : 0453-4654
ISSN-L : 0453-4654
Direct-Vision-Based Reinforcement Learning Using a Layered Neural Network
For the Whole Process from Sensors to Motors
Katsunari SHIBATAYoichi OKABEKoji ITO
Author information
JOURNAL FREE ACCESS

2001 Volume 37 Issue 2 Pages 168-177

Details
Abstract
In this paper, Direct-Vision-Based Reinforcement Learning is proposed not only for the learning of motion but for the learning of the whole process, which includes recognition, from sensors to motors in robots. In this learning, raw visual sensory signals are put into a layered neural network directly, and the network is trained by Back Propagation using the training signal generated based on reinforcement learning. By employing neural network, whole the process becomes seamless and is trained purposively and harmonically.
Two simulations of the mobile robot with visual sensors are performed as examples. One task requires stereo-vision, and the other requires obstacle avoidance. By observing the hidden representation in the neural network, it is shown that some abstract representation of spatial recognition is formed without any advance knowledge.
Finally it is shown that each visual sensory cell makes a role of localization of the global information of the space and it helps the fast and stable learning.
Content from these authors
© The Society of Instrument and Control Engineers (SICE)
Previous article Next article
feedback
Top