Design Strategies for Evolutionary Robotics

  title={Design Strategies for Evolutionary Robotics},
  author={Andrew Murray and Sushil J. Louis},
This paper deals with the question of how to balance evolutionary design and human expertise in order to best design robots which can learn speciic tasks. We study two behavioral tasks, approach and avoidance, and provide some preliminary results. 
Adapting Control Strategies for Situated Autonomous
This paper studies how to balance evolutionary design and human expertise in order to best design situated autonomous agents which can learn speciic tasks. A genetic algorithm designs controlExpand
Evolutionary self-organization of an artificial potential field map with a group of autonomous robots
  • Jiming Liu, James S. Wu, D. Maluf
  • Computer Science, Medicine
  • Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406)
  • 1999
An evolutionary self-organization approach to collective task handling is developed and demonstrated in tackling the specific problem of collectively constructing a global spatial representation, i.e., an artificial potential field map, in an unknown environment. Expand
Multi-phase sumo maneuver learning
A multi-phase genetic programming (MPGP) approach to an autonomous robot learning task, where a sumo wrestling robot is required to execute specialized pushing maneuvers in response to different opponents' postures, is demonstrated. Expand
Embodied artificial life at an impasse can evolutionary robotics methods be scaled?
  • A. Nelson
  • Engineering, Computer Science
  • 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)
  • 2014
It is made the case that common tasks used to demonstrate the effectiveness of evolutionary robotics are not characteristic of more general cases and in fact do not fully prove the concept that artificial evolution can be used to evolve sophisticated autonomous agent behaviors. Expand
Research on obstacle avoidance method for evolutionary robot based on artificial neural network
Obstacle avoidance behavior learning of evolutionary robot is realized by the use of artificial neural network in this paper. First, a robot learning environment and a robot model are presented andExpand
Learning coordinated maneuvers in complex environments: a sumo experiment
A dual-agent system capable of learning eye-body-coordinated maneuvers in playing a sumo contest with a multi-phase genetic-programming approach aimed to enable the player to gradually acquire sophisticated sumo maneuvers is described. Expand
Combining Control Strategies Using Genetic Algorithms with Memory
A genetic algorithm augmented with a long term memory is used to design control strategies for a simulated robot, a mobile vehicle operating in a two-dimensional environment that quickly combines the basic behaviors and finds control Strategies for performing well in the more complex environment. Expand
Towards Behavior Control for Evolutionary Robot Based on RL with ENN
The experimental results have demonstrated that the proposed algorithm can perform the decision-making strategy and parameter setup optimization of ANN and GA by learning and can effectively escape from a trap of local minima, avoid motion deadlock status of humanoid soccer robotic agents, and reduce the oscillation of the planned trajectory among the multiple obstacles by crossover and mutation. Expand
Towards Behavior Switch Control for an Evolutionary Robot Based on RL with ENN
This method is able not only to construct the reinforcement learning models for autonomous robots and evolutionary robot modules that control behaviors and reinforcement learning environments, and to perform the behavior-switching control and obstacle avoidance of an evolutionary robotics (ER) in time-varying environments with static and moving obstacles by combining ANN and GA. Expand
Using Genetic Algorithms to Design Control Strategies for Simulated Robots
i Acknowledgments I would rst like to express my appreciation to Dr. Sushil J. Louis, my thesis advisor, for his guidance and support throughout this research. It was he that initiated and nurturedExpand


Adapting Control Strategies for Situated Autonomous
This paper studies how to balance evolutionary design and human expertise in order to best design situated autonomous agents which can learn speciic tasks. A genetic algorithm designs controlExpand
Designer Genetic Algorithms: Genetic Algorithms in Structure Design
A genetic algorithm is described that uses di erential information about search direction to design structures that is captured by a masked crossover operator which also removes the bias toward short schemas. Expand
Evolving visually guided robots
Results are presented which demonstrate that neural network control architectures can be evolved for an accurate simulation model of a visually guided robot. Expand
Genetic Algorithms in Search Optimization and Machine Learning
This book brings together the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields. Expand
Adaptation in natural and artificial systems
Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI. Expand
Robot shaping: developing situated agents through learning
Modular row housing used to construct row housing units of one story or more comprising a plurality of modular units, each having a height of one story and a width corresponding to one-half of theExpand
\Design strategies for evolutionary robotics
  • Proceedings of the Third Golden West International Conference on Intelligent Systems
  • 1995
Husbands, and I. Harvey. \Evolving visually guided robots
  • Husbands, and I. Harvey. \Evolving visually guided robots
  • 1992
Adaptation In Natural and Arti cial Systems. The University of Michigan Press
  • Ann Arbour,
  • 1975