Book Chapter10.1007/3-540-45723-2_49
Evolving Brain Structures for Robot Control
Frank Pasemann,Frank Pasemann,Uli Steinmetz,Martin Hülse,Bruno Lara +4 more
- 13 Jun 2001
- pp 410-417
TL;DR: To study the relevance of recurrent neural network structures for the behavior of autonomous agents a series of experiments with miniature robots is performed and solutions for obstacle a voidance and phototropic behavior are presented.
read more
Abstract: To study the relevance of recurrent neural network structures for the behavior of autonomous agents a series of experiments with miniature robots is performed. A special evolutionary algorithm is used to generate netw orks of different sizes and architectures. Solutions for obstacle a voidance and phototropic behavior are presented. Netw orks are evolved with the help of simulated robots, and the results are validated with the use of physical robots.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Fitness functions in evolutionary robotics: A survey and analysis
TL;DR: Current ER research is surveyed according to the degree of a priori knowledge used to formulate the various fitness functions employed during evolution to identify methods that allow the development of the greatest degree of novel control, while requiring the minimum amount of aPriori task knowledge from the designer.
339
EDHMoR: Evolutionary designer of heterogeneous modular robots
TL;DR: The coevolution of morphology and control in robots is analyzed and a particular strategy to address this problem is contemplated and a constructive evolutionary algorithm based on tree-like representations of the morphology is proposed that can intrinsically provide for a type of generative evolutionary approach.
58
Complex environments, complex behaviour
TL;DR: A modular NN design was used in conjunction with evolutionary algorithm methods to evolve an animat capable of learning behavioural patterns at several levels of complexity.
4
Evolution of multiple gaits for modular robots
Vojtech Vonasek,Jan Faigl +1 more
- 01 Dec 2016
TL;DR: This paper investigates how to automatically derive a set of gaits suitable for modular robots without specifying low-level details about the gaits and proposes to optimize multiple gaits simultaneously using a single cost function.
1
Competitive Relative Performance and Fitness Selection for Evolutionary Robotics
Andrew L. Nelson
- 21 May 2003
TL;DR: The case is made that current methods of fitness selection represent the primary factor limiting the further development of ER, and a fitness function specification is formulated that accommodates the Bootstrap Problem during early evolution, but that limits human bias in selection later in evolution.
References
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Stefano Nolfi,Dario Floreano +1 more
- 01 Mar 2004
TL;DR: This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far, and describes the clear presentation of a set of empirical experiments of increasing complexity.
Evolutionary robotics: The biology, intelligence, and technology of self‐organizing machines
TL;DR: A new book enPDFd evolutionary robotics the biology intelligence and technology of self organizing machines intelligent robotics and autonomous agents series to read.
1.2K
Evolution Versus Design: Controlling Autonomous Robots
Phil Husbands,Inman Harvey +1 more
- 08 Jul 1992
TL;DR: It is argued that the most useful basic building blocks for an evolved cognitive archite(*t ?
44
Evolving neurocontrollers for balancing an inverted pendulum.
TL;DR: An evolutionary algorithm that is tailored to generate recurrent neural networks functioning as nonlinear controllers that solve the pole-balancing problem, i.e. balancing an inverted pendulum is introduced.
Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms
Francesco Mondada,Edoardo Franzi,Paolo Ienne +2 more
- 28 Oct 1993
TL;DR: The interaction of an autonomous mobile robot with the real world critically depends on the robots morphology and on its environment Building a model of these aspects is extremely complex, making simulation insufficient for accurate validation of control algorithms as mentioned in this paper.