Corpus ID: 15233497

Evolutionary robotics and SAGA: The case for hill crawling and tournament selection

@inproceedings{Harvey1994EvolutionaryRA,
  title={Evolutionary robotics and SAGA: The case for hill crawling and tournament selection},
  author={Inman R. Harvey},
  year={1994}
}
This paper will look at an evolutionary ap proach to robotics partly at pragmatic issues but primarily at theoretical issues associated with the evolutionary algorithms which are ap propriate Genetic Algorithms are not suitable in their usual form for the evolution of cogni tive structures which must be in an incremental fashion SAGA Species Adaptation Genetic Algorithms is a conceptual framework for ex tending GAs to variable length genotypes where evolution allows a species of individuals to… Expand

Figures from this paper

Artiicial Evolution and Real Robots 2 Artiicial Evolution for Robots
Arti cial evolution as a design methodology allows the relaxation of many of the constraints that have held back conventional methods It does not require a complete prior analysis and decompositionExpand
Evolutionary Robotics at Sussex
We give an overview of evolutionary robotics research at Sussex. We explain and justify our distinctive approaches to (artiicial) evolution, and to the nature of robot control systems that areExpand
Artificial evolution and real robots
  • I. Harvey
  • Computer Science
  • Artificial Life and Robotics
  • 2006
TLDR
Examples of evolved robots will be discussed, including a specialized piece of equipment which allows a robot to be tested using simple vision in real time, and what is believed to be the first successful example of an evolved hardware controller for a robot. Expand
Adaptive networks for robotics and the emergence of reward anticipatory circuits
TLDR
This thesis proposes a formal model of functional integration, encompassing locomotion and sequence learning, and presents some ideas on how the co-evolution of GasNet and reward adaptive circuits might lead to significant improvements in the synthesis of agents capable of exhibiting complex adaptive behaviour. Expand
Explorations in Evolutionary Robotics
TLDR
Results demonstrate that robust visually guided control systems evolve from evaluation functions that do not explicitly require monitoring visual input, and propose an automatic design process involving artificial evolution, wherein the basic building blocks for evolving cognitive architectures are noise-tolerant dynamical neural networks. Expand
Evolutionary neurocontrollers for autonomous mobile robots
TLDR
A methodology for evolving neurocontrollers of autonomous mobile robots without human intervention is described and an evolved neurocontroller that relies on fast and continuously changing synapses characterized by dynamic stability is investigated. Expand
An experimental design framework for evolutionary robotics
TLDR
This thesis outlines one approach to the design and development of a robot, controlled by a neural network, by combining the work of a number of researchers in the areas of machine intelligence and artificial life. Expand
Artificial evolution of visual control systems for robots
TLDR
Analytic techniques drawn from neuroethology and dynamical systems theory allow us to understand how the evolved robot controllers function, and to predict their behaviour in environments other than those used during the evolutionary process. Expand
Evolutionary R Obotics at Sussex
We give a n o verview of evolutionary robotics research at Sussex. We e x-plain and justify our distinctive approaches to (artiicial) evolution, and to the nature of robot control systems that areExpand
Evolutionary Robot Behaviors Based on Natural Selection and Neural Network
TLDR
This paper has created and described an artificial world containing autonomous organisms for developing and testing some novel ideas, and focuses on the principles of developmental modularity based on neural networks. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Evolving Visually Guided Robots Evolving Visually Guided Robots
We have developed a methodology grounded in two beliefs: that autonomous agents need visual processing capabilities , and that the approach of hand-designing control architectures for autonomousExpand
Adaptation in natural and artificial systems
TLDR
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
Applications of concurrent neuromorphic algorithms for autonomous robots
TLDR
An overview of studies at the Oak Ridge National Laboratory (ORNL) of neural networks running on parallel machines applied to the problems of autonomous robotics is provided. Expand
Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems
TLDR
In this new "genetic programming" paradigm, populations of computer programs are genetically bred using the Darwinian principle of survival of the fittest and using a genetic crossover (recombination) operator appropriate for genetically mating computer programs. Expand
Achieving Artificial Intelligence through Building Robots
We argue that generally accepted methodologies of artificial intelligence research are limited in the proportion of human level intelligence they can be expected to emulate. We argue that theExpand
Intelligence without Representation
TLDR
The fundamental decomposition of the intelligent system is not into independent information processing units which must interface with each other via representations, but into independent and parallel activity producers which all interface directly to the world through perception and action. Expand
Towards an Optimal Mutation Probability for Genetic Algorithms
TLDR
In this paper the optimal parameter setting of Genetic Algorithms (GAs) is investigated and a heuristic comprising these results is presented. Expand
A learning system based on genetic adaptive algorithms
TLDR
This thesis is concerned with investigating the feasibility of constructing a general purpose learning system around a particular class of domain independent methods called genetic algorithms, and a specific learning system organization, LS-1, is proposed. Expand
On the design of devices with emergent semantic functions
TLDR
This dissertation explores how to go about designing self-organizing devices which adaptively construct their own relationships to the physical world (emergent semantic functions), and bears on the frame/feature-generation problem in artificial intelligence, the problem of machine creativity in philosophy, the measurement problem in physics, the Problem of generating new observables in science, and theproblem of emergent functions in evolutionary biology. Expand
The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best
TLDR
This paper reports work done over the past three years using rank-based allocation of reproductive trials to suggest that allocating reproductive trials according to rank is superior to tness proportionate reproduction. Expand
...
1
2
3
...