Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot
Dario Floreano,Francesco Mondada +1 more
- pp 421-430
Reads0
Chats0
TLDR
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot, and shows a number of emergent phenomena that are characteristic of autonomous agents.Abstract:
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot. The evolutionary approach to the development of neural controllers for autonomous agents has been successfully used by many researchers, but most - if not all - studies have been carried out with computer simulations. Instead, in this research the whole evolutionary process takes places entirely on a real robot without human intervention. Although the experiments described here tackle a simple task of navigation and obstacle avoidance, we show a number of emergent phenomena that are characteristic of autonomous agents. The neural controllers of the evolved best individuals display a full exploitation of non-linear and recurrent connections that make them more efficient than analogous man-designed agents. In order to fully understand and describe the robot behavior, we have also employed quantitative ethological tools [13], and showed that the adaptation dynamics conform to predictions made for animals.read more
Citations
More filters
Book ChapterDOI
P\(\mathrm {\Phi }\)SS: An Open-Source Experimental Setup for Real-World Implementation of Swarm Robotic Systems in Long-Term Scenarios
TL;DR: The platform combines a versatile open-hardware micro-robot capable of local and global communication, commercially-available wireless charging modules which provide virtually unlimited robot operation time and an open-source marker-based robot tracking system for automated experiment evaluation.
Proceedings ArticleDOI
On using Gene Expression Programming to evolve multiple output robot controllers
Jonathan Mwaura,Edward Keedwell +1 more
TL;DR: This paper investigates the parallelisation of genes as independent chromosome entities as described in the Gene Expression Programming (GEP) algorithm and shows that moGEP is a robust technique for the investigated problem class as well as for utilisation in evolutionary robotics.
Dissertation
Evolution of self-organising behaviours with novelty search
TL;DR: This thesis proposes Progressive Minimal Criteria Novelty Search (PMCNS), a novel method for combining novelty and objectives, where the exploration of the behaviour space is progressively restricted to zones of increasing fitness scores, and shows that PMCNS can improve the fitness scores of the evolved solutions, without compromising the diversity of behaviours.
Proceedings ArticleDOI
On an immuno-inspired distributed, embodied action-evolution cum selection algorithm
TL;DR: This paper proposes an immunology-inspired embodied action-evolution cum selection algorithm that can cater to distributed ER and shows that a repertoire of antibody-like subcontrollers was created, evolved and shared on-the-fly to cope up with different environmental conditions.
References
More filters
Book
Genetic algorithms in search, optimization, and machine learning
TL;DR: In this article, the authors present the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields, including computer programming and mathematics.
Book
Adaptation in natural and artificial systems
TL;DR: Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.
Intelligence without Representation
TL;DR: Brooks et al. as mentioned in this paper decompose an intelligent system into independent and parallel activity producers which all interface directly to the world through perception and action, rather than interface to each other particularly much.
Journal ArticleDOI
Intelligence without representation
TL;DR: Brooks et al. as discussed by the authors decompose an intelligent system into independent and parallel activity producers which all interface directly to the world through perception and action, rather than interface to each other particularly much.