Evolutionary robotics

Résumé

Evolutionary robotics is an embodied approach to Artificial Intelligence (AI) in which robots are automatically designed using Darwinian principles of natural selection. The design of a robot, or a subsystem of a robot such as a neural controller, is optimized against a behavioral goal (e.g. run as fast as possible). Usually, designs are evaluated in simulations as fabricating thousands or millions of designs and testing them in the real world is prohibitively expensive in terms of time, money, and safety. An evolutionary robotics experiment starts with a population of randomly generated robot designs. The worst performing designs are discarded and replaced with mutations and/or combinations of the better designs. This evolutionary algorithm continues until a prespecified amount of time elapses or some target performance metric is surpassed. Evolutionary robotics methods are particularly useful for engineering machines that must operate in environments in which humans have limited in

Source officielle

https://en.wikipedia.org/wiki/Evolutionary_robotics

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (56)

Publications associées

Chargement

Personnes associées (5)

, , , ,

Personnes associées

Chargement

Unités associées (6)

Unités associées

Chargement

Concepts associés (6)

Concepts associés

Chargement

Cours associés (2)

Cours associés

Chargement

Séances de cours associées (1)

Séances de cours associées

Chargement

Evolutionary adaptive robots

Joseba Urzelai

EPFL2000

Chargement

Dynamic Resolution in the Co-Evolution of Morphology and Control

Joshua Evan Auerbach

Evolutionary robotics is a promising approach to overcoming the limitations and biases of human designers in producing control strategies for autonomous robots. However, most work in evolutionary robotics remains solely concerned with optimizing control strategies for existing morphologies. By contrast, natural evolution, the only process that has produced intelligent agents to date, may modify both the control (brain) and morphology (body) of organisms. Therefore, co-evolving morphology along with control may provide a better path towards realizing intelligent robots. This paper presents a novel method for co-evolving morphology and control using CPPN-NEAT. This method is capable of dynamically adjusting the resolution at which components of the robot are created: a large number of small sized components may be present in some body locations while a smaller number of larger sized components is present in other locations. Advantages of this capability are demonstrated on a simple task, and implications for using this methodology to create more complex robots are discussed.

MIT Press2010

Chargement

Evolving Monolithic Robot Controllers through Incremental Shaping

Joshua Evan Auerbach

Evolutionary robotics has been shown to be an effective technique for generating robot behaviors that are difficult to derive analytically from the robot’s mechanics and task environment. Moreover, augmenting evolutionary algorithms with environmental scaffolding via an incremental shaping method makes it possible to evolve controllers for complex tasks that would otherwise be infeasible. In this paper we present a summary of two recent publications in the evolutionary robotics literature demonstrating how these methods can be used to evolve robot controllers for non-trivial tasks, what the obstacles are in evolving controllers in this way, and present a novel research question that can be investigated under this framework.

Springer Berlin Heidelberg2011

Chargement