Due to the limitations of sensors, each member of a decentralized system can only deal with local information respectively. A description of local relationship within formation pattern is proposed in this paper. Furthermore, a NN control approach with robust term is proposed to control individual motion. By using such individual control method, all robots will finally form a unique formation. Based on properties of such control strategy, we propose a modified artificial potential approach to realize obstacle avoidance.
|Number of pages||6|
|Journal||Lecture Notes in Computer Science|
|Publication status||Published - 26 Sep 2005|
|Event||Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China|
Duration: 30 May 2005 → 1 Jun 2005
ASJC Scopus subject areas
- Computer Science (miscellaneous)