Controlling a truck with an adaptive critic CMAC design
Article Abstract:
In this study, CMAC (Cerebellar Model Articulated Controller) neural architectures are shown to be viable for the purposes of real-time learning and control. An adaptive critic neuro-control design has been implemented that learns in real-time how to back up a trailer truck along a fixed straight line trajectory. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. (Reprinted by permission of the publisher.)
Publication Name: SIMULATION
Subject: Engineering and manufacturing industries
ISSN: 0037-5497
Year: 1992
User Contributions:
Comment about this article or add new information about this topic:
Guidelines for the design of data driven generic simulators for specific domains
Article Abstract:
Data-driven generic simulators have, for many years, been used to model a wide range of systems. Some such simulators are promoted as general purpose, while others are specific to particular problem domains. This paper considers how domain-specific data-driven simulators should be constructed using a modular approach which allows the simulator to be incrementally enhanced and ported easily to alternative computing environments. It also argues that generic simulators will not wholly replace simulation programming for specific applications. (Reprinted by permission of the publisher.)
Publication Name: SIMULATION
Subject: Engineering and manufacturing industries
ISSN: 0037-5497
Year: 1992
User Contributions:
Comment about this article or add new information about this topic: