China
Africa
Explore chapters and articles related to this topic
Robotic Path-Planning in Dynamic and Uncertain Environment Using Genetic Algorithm
Published in Jitendra R. Raol, Ajith K. Gopal, Mobile Intelligent Autonomous Systems, 2016
As we have seen in Chapter 1, GAs have been found to be very effective methods for solving multi-criteria/multi-objective optimization problems in science and engineering. The GAs mimic models of natural evolution and possess an ability to adaptively search large spaces in near-optimal, often global optimal, ways. One important application of the GA is in the area of evolutionary robotics. In this field, GA is used for designing behavioural controllers for robots and autonomous agents for autonomous mobile vehicles. Especially, GA can be used for path-planning (PPGA) that proposes the evolution of a chromosome attitudes structure to control a simulated mobile robot [13]. These attitudes specify the basic robot actions to reach a goal point. The PPGA performs straight motions and avoids obstacles. The fitness function employed to teach robot’s movements is designed to achieve this type of behaviour in spite of any changes in the robot’s goals and environment aspects. This learning process in this PPGA is not dependent on the obstacle environment distribution. Also, it does not depend on the initial and final points. Hence, this PPGA-based controller is not required to be retrained when these parameters change.
Emergence of Intelligence
Published in Hitoshi Iba, AI and SWARM, 2019
Evolutionary robotics [84] is a method for producing autonomous robots via evolutionary processes. In other words, it is an attempt to train appropriate robot behavior by representing the robot control system as a genotype and then applying EA search techniques.
On building a person: benchmarks for robotic personhood
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2020
Technically, the materials out of which a being is constructed is not really a criterion of personhood. Personhood as understood here deals with behavioral competences of beings, not with how their bodies are constructed. Even so, if a Cyberiad of robots is to survive, it requires either that the original robots persist, or are replaced by other robots, and in either case, we need to explain how this is possible. In the case of persistence, how is it possible for the robots not eventually to fall apart, or for their competences to break down in various ways? And, how are they to obtain energy and perform work, against entropic forces? In the case of replacements, is there a process by which to guarantee that their replacements are no worse in competence than the robots they replace? And how are these robots constructed, when organic processes are not involved? Interestingly, some of these issues have been tackled in recent work in Evolutionary Robotics (Bongard, 2013; Doncieux et al., 2015; Floreano, Husbands, & Nolfi, 2008; Floreano & Keller, 2010; Jelisavcic et al., 2017; Lipson & Pollack, 2000; Nolfi & Floreano, 2000; Weel, Crosato, Heinerman, Haasdijk, & Eiben, 2014; Yang et al., 2018; Zykov, Mytilinaios, Adams, & Lipson, 2005).