Genetic programming
Related papers: 20
About
Genetic programming (GP) is an evolutionary computation technique that automatically generates computer programs by mimicking biological natural selection. Starting from a population of randomly generated programs, typically represented as tree structures, GP iteratively applies selection, crossover, and mutation operators to produce increasingly capable solutions over successive generations — effectively allowing computers to write and refine their own code. In robotics and AI, GP is used to automatically synthesize control programs, locomotion strategies, sensor-processing routines, and behavior arbitrators without requiring engineers to hand-code every detail. Applications range from evolving walking gaits for legged robots and snake-like locomotion patterns, to coordinating multi-robot teams, calibrating industrial manipulators, and generating image analysis pipelines. GP can simultaneously optimize both a robot's control logic and its physical configuration in modular systems. GP matters because it dramatically reduces manual programming effort while discovering novel, human-competitive solutions that engineers might not intuitively conceive. Its ability to handle complex, nonlinear, and high-dimensional design spaces makes it particularly valuable when robot behavior requirements are difficult to specify analytically, enabling autonomous adaptation and emergent intelligence in real-world deployment scenarios.
Top Researchers
Top Institutes
Top Cited Papers
Genetic Programming: On the Programming of Computers by Means of Natural Selection
John R. Koza
Citations: 13277 • 1992
Human-competitive results produced by genetic programming
John R. Koza
Citations: 321 • 2010
Hierarchical genetic algorithms operating on populations of computer programs
John R. Koza
Citations: 294 • 1989
Artificial Life and Real Robots
Rodney A. Brooks
Citations: 259 • 1992
Computational Intelligence: Methods and Techniques
Leszek Rutkowski
Citations: 247 • 2008
Genetic Programming for Image Analysis
Citations: 183 • 1996
Genetic programming approach to the construction of a neural network for control of a walking robot
M. Anthony Lewis, Andrew H. Fagg, A. Solidum
Citations: 170 • 2003
Co-evolving Soccer Softbot team coordination with genetic programming
Sean Luke, Charles Hohn, Jonathan Farris, Gary Jackson, James Hendler
Citations: 148 • 1998
EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine
Hugo de Garis
Citations: 134 • 1993
Recent developments in evolutionary and genetic algorithms: theory and applications
Nachol Chaiyaratana
Citations: 126 • 1997
Multi-robot path planning using co-evolutionary genetic programming
Rahul Kala
Citations: 124 • 2011
An On-Line Method to Evolve Behavior and to Control a Miniature Robot in Real Time with Genetic Programming
Peter Nordin, Wolfgang Banzhaf
Citations: 121 • 1997
Simbad: An Autonomous Robot Simulation Package for Education and Research
Louis Hugues, Nicolas Bredèche
Citations: 104 • 2006
Automated evolutionary design, robustness, and adaptation of sidewinding locomotion of a simulated snake-like robot
Ivan Tanev, Thomas S. Ray, Andrzej Buller
Citations: 101 • 2005
Genetic network programming - application to intelligent agents
Hideki Katagiri, K. Hirasama, Junyi Hu
Citations: 88 • 2002
Automatic programming of robots using genetic programming
John R. Koza, James P. Rice
Citations: 87 • 1992
Programming cells: towards an automated ‘Genetic Compiler’
Kevin Clancy, Christopher A. Voigt
Citations: 86 • 2010
Trustworthy Genetic Programming-Based Synthesis of Analog Circuit Topologies Using Hierarchical Domain-Specific Building Blocks
Trent McConaghy, Pieter Palmers, Michiel Steyaert, Georges Gielen
Citations: 78 • 2011
Evaluation of genetic programming-based models for simulating bead dimensions in wire and arc additive manufacturing
Biranchi Panda, K. Shankhwar, Akhil Garg, M. M. Savalani
Citations: 74 • 2016
Layered Learning in Genetic Programming for a Cooperative Robot Soccer Problem
Steven Gustafson, William H. Hsu
Citations: 69 • 2001