Neuroevolution: Real-Time Creation of Sequential Digital Systems for Control, Design, and Decision Making

Background Many applications lack a method of evolving networks for learning tasks. In difficult real-world learning tasks such as controlling robots, playing games, or pursuing or evading an enemy, there are no direct targets that can specify the correct action for every situation. Neural networks promise to solve this problem, but a long process of training must occur before it can be effective. A new system for the training of neural networks is needed and can be used to solve a number of problems.

Invention Description Real-time NeuroEvolution of Augmenting Topologies (rtNEAT) is a genetic algorithm that trains and evolves neural networks of increasing complexity from a minimal starting point. This means networks that succeed continue while others are discarded, avoiding the problem of preparatory (non-real-time) training. Agents governed by rtNEAT neural networks can learn processes and even invent new solutions based on feedback without the guidance of a human programmer or controller, freeing the programmer from having to script extensive behaviors.

Benefits

Can find solutions efficiently in real-time Can solve new problems without training Can discover novel solutions Evolves increasingly optimal and complex controllers Can be universally installed in systems Broad range of beneficial applications

Features

Continual, indefinite evolution Evolution occurs in real-time rather than at fixed intervals while the user has to wait Behavioral responses to environment and scenarios Packaged as a software development kit

Market Potential/Applications Since NEAT and rtNEAT are general algorithms for evolving controllers, any application involving the automated control of some process, object, vehicle or sensory system could be viable. This technology currently is being directed towards the video game industry for the possibility of evolving characters in games and massive multiplayer online games. The uses for this algorithm, however, can be expanded to military simulations, educational games and applications, robotics, vehicle control systems, factories or as a research tool for modeling. The algorithms could also be implemented in pattern recognition and prediction applications.

Development Stage Beta product/commercial prototype

IP Status One U.S. patent application filed

UT Researcher Risto P. Miikkulainen, Ph.D., Computer Sciences, The University of Texas at Austin Kenneth O. Stanley, Ph.D., Computer Sciences, The University of Texas at Austin

Type of Offer: Licensing



« More Computer Science Patents

---