Developing robotic behavior using a genetic programming model

Abstract

Issued by Sandia National Laboratories, operated for the United States Department of Energy by San&a Corporation. NOTICE This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, nor any of their contractors, subcontractors, or their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process &sclosed, or represents that its use would not infringe privately owned rights. Reference herein t o any specific commercial product, process, or service by trade name, trademark, manufacturer, o r otherwise, does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government, any agency thereof, or any of their contractors or subcontractors. The views and opinions expressed herein do not necessarily state or reflect those of the United States Government, any agency thereof, or any of their contractors.

Autonomous Dynamic Soaring Platform for Distributed Mobile Sensor Arrays

“…This part of the project extends the work of Pryor [1998] and Barnette et al [2000] who applied evolutionary methods to the development of robotic behavior. Pryor [1998] originally developed a genetic programming model to solve a suite of high-level robotics problems.…”

“…Pryor [1998] originally developed a genetic programming model to solve a suite of high-level robotics problems. The motion of Pryor's "robugs" was idealized and highly constrained so that the focus of his evolutionary model could be on high-level navigational behaviors and goals.…”

“…Terminals return values that result in an instruction to the robot. The trees themselves are generated by a genetic programming model originally developed by Pryor [1998] and based on methods described by Koza [1992], within a general framework presented by Holland [1975]. Genetic programming is a type of genetic algorithm, an evolutionary computing method that is based on the principles of biological evolution.…”

Developing close combat behaviors for simulated soldiers using genetic programming techniques.

“…Welldeveloped descriptions of genetic programming can be found in previous papers in this sequence (see Pryor, 1998 and2002), or in any of several books. The seminal work in genetic programming, Genetic Programming: On the Programming of Computers by Means of Natural Selection, was written by John Koza, the methodology's inventor, and is extremely accessible and informative.…”

“…The first phase investigated the use of genetic programming to produce behaviors for simple robots. A full account of that research can be found in Pryor, 1998. The second phase determined that genetic programs were capable of developing agent behaviors that pursued several goals simultaneously.…”