If it evolves it needs to learn
A. E. Eiben, Emma Hart
Abstract
We elaborate on (future) evolutionary robot systems where morphologies and controllers of real robots are evolved in the real-world. We argue that such systems must contain a learning component where a newborn robot refines its inherited controller to align with its body, which will inevitably be different from its parents.
Topics & Concepts
Component (thermodynamics)RobotComputer scienceController (irrigation)Artificial intelligenceHuman–computer interactionControl engineeringEngineeringBiologyAgronomyThermodynamicsPhysicsModular Robots and Swarm IntelligenceReinforcement Learning in RoboticsRobot Manipulation and Learning