Challenges and Opportunities of Evolutionary Robotics - Computer Science > Neural and Evolutionary ComputingReportar como inadecuado




Challenges and Opportunities of Evolutionary Robotics - Computer Science > Neural and Evolutionary Computing - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: Robotic hardware designs are becoming more complex as the variety and numberof on-board sensors increase and as greater computational power is provided inever-smaller packages on-board robots. These advances in hardware, however, donot automatically translate into better software for controlling complexrobots. Evolutionary techniques hold the potential to solve many difficultproblems in robotics which defy simple conventional approaches, but presentmany challenges as well. Numerous disciplines including artificial life,cognitive science and neural networks, rule-based systems, behavior-basedcontrol, genetic algorithms and other forms of evolutionary computation havecontributed to shaping the current state of evolutionary robotics. This paperprovides an overview of developments in the emerging field of evolutionaryrobotics, and discusses some of the opportunities and challenges whichcurrently face practitioners in the field.



Autor: D. A. Sofge, M. A. Potter, M. D. Bugajska, A. C. Schultz

Fuente: https://arxiv.org/







Documentos relacionados