Evolvability, Environments, Embodiment, & Emergence in Robotics

Front Cover
John H. Long, Eric Aaron, Stéphane Doncieux
Frontiers Media SA, Nov 8, 2018 - Engineering (General). Civil engineering (General) - 109 pages

 Embodied and evolving systems — biological or robotic — are interacting networks of structure, function, information, and behavior.  Understanding these complex systems is the goal of the research presented in this book.  We address different questions and hypotheses about four essential topics in complex systems: evolvability, environments, embodiment, and emergence. Using a variety of approaches, we provide different perspectives on an overarching, unifying question: How can embodied and evolutionary robotics illuminate (1) principles underlying biological evolving systems and (2) general analytical frameworks for studying embodied evolving systems?  The answer — model biological processes to operate, develop, and evolve situated, embodied robots.  

 

Selected pages

Contents

Evolvability Environments Embodiment Emergence in Robotics
4
Integrated Intelligence Modeling for GoalDirected Embodied Agents
7
A New Frontier for Evolutionary Computation
27
On the Critical Role of Divergent Selection in Evolvability
44
Why So Difficult?
51
Morphological Modularity Can Enable the Evolution of Robot Behavior to Scale Linearly with the Number of Environmental Features
62
Evolution of Neural Net Controllers in Physically Embodied Robots
72
Epigenetic Operators and the Evolution of Physically Embodied Robots
88
Back Cover
108
Copyright

Common terms and phrases

adaptive aligned BC Ana BBot approach behavioral diversity Bongard Bredeche Clune cognitive elements cognitive–physical integration complex Conference on Genetic connections connectome controller crossover placement crossover points deliberative Development Type DI-HDCA modeling DirectionBC Doncieux drives search dynamical intention dynamical system effect embodied agents encoded EndpointBC environment space evolutionary algorithms Evolutionary Computation evolutionary robotics evolvability experiments Figure fitness landscape framework function Genetic and Evolutionary genome goal goal-directed gskill Hebbian learning hidden layer hidden nodes hybrid increasing individuals inputs intelligence LDRs learning Lehman and Stanley machine learning MAP-Elites Miikkulainen mode morphology motor output Mouret multi-BC mutation navigation neural networks novelty search number of threads optimization parameters performance phenotypes phototaxis physical robots pin group population possible potential QD algorithms QD-score reactive represent runBases runs sensors simulated small maze sparsity symmetric gauntlet Tadro Tag game target tion unaligned BC Vassar College wires

Bibliographic information

TitleEvolvability, Environments, Embodiment, & Emergence in Robotics
Frontiers Research Topics
EditorsJohn H. Long, Eric Aaron, Stéphane Doncieux
PublisherFrontiers Media SA, 2018
ISBN2889456226, 9782889456222
Length109 pages
  
Export CitationBiBTeX EndNote RefMan