Biological information processing systems can be said as one of the ultimate decentralized systems, and have been expected to provide various fruitful ideas to engineering fields, especially robotics. Among these systems, brain-nervous system and genetic system have already been widely used by modeling as neural networks and genetic algorithms, respectively. On the other hand, immune system also plays an important role to cope with dynamically changing environment by constructing self-nonself recognition networks among different species of antibodies. And this system has a lot of interesting features such as learning, self-organizing abilities and so on viewed from the engineering standpoint. However, immune system has not yet been applied to engineering fields so far notwithstanding its important role. In this paper, we propose a new hypothesis concerning the structure of immune system, called mutual-coupled immune networks hypothesis, based on recent studies on immunology. And we apply this idea to gait acquisition of a hexapod walking robot as a practical example. Finally, the feasibility of our proposed method is confirmed by simulations.
|Number of pages||6|
|Publication status||Published - 1995 Dec 1|
|Event||Proceedings of the 1995 IEEE International Conference on Evolutionary Computation. Part 1 (of 2) - Perth, Aust|
Duration: 1995 Nov 29 → 1995 Dec 1
|Other||Proceedings of the 1995 IEEE International Conference on Evolutionary Computation. Part 1 (of 2)|
|Period||95/11/29 → 95/12/1|
ASJC Scopus subject areas