Simulated annealing and Boltzmann machines: a stochastic approach to combinatorial optimization and neural computing
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Intelligent Optimisation Techniques: Genetic Algorithms, Tabu Search, Simulated Annealing and Neural Networks
On the quasi-Newton training method for feed-forward neural networks
CompSysTech '04 Proceedings of the 5th international conference on Computer systems and technologies
| Hi-index | 0.00 |
This paper describes how industrial applications were targeted and successfully implemented by robotic manipulators that have been developed from studies in embodied artificial intelligent systems. The goal was to design mobile, flexible and self-learning manipulators that allow to perform multiple tasks with very short preparation time, a reasonable working speed and, at the same time, in a human-like manner. The advantages and disadvantages of these solutions compared to traditional industrial robot applications had to be considered continuously to concentrate on the right market segments, applications and customers. Thus, in addition to develop the appropriate requirements of real-time executions, risk analyses and usability, studies were established and implemented in collaboration with scientists, integrators and end customers. Acceptance, impacts of the revolution in personal intelligent robotics as well as challenges to overcome in the future are discussed.