期刊
IEEE ACCESS
卷 8, 期 -, 页码 140558-140568出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3012886
关键词
Path planning; Real-time systems; Three-dimensional displays; Robots; Multi-robot systems; Neurons; Task analysis; Heterogeneous multi-robot system; path planning; dragonfly algorithm; bio-inspired neural network
资金
- National Natural Science Foundation of China [61873086]
- Jiangsu Province Natural Science Foundation [BK20170305]
- Fundamental Research Funds for the Central Universities [2018B23214]
Heterogeneous multi-robot system is one of the most important research directions in the robotic field. Real-time path planning for heterogeneous multi-robot system under unknown 3D environment is a new challenging research and a hot spot in this field. In this paper, an improved real-time path planning method is proposed for a heterogeneous multi-robot system, which is composed of many unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). In the proposed method, the 3D environment is modelled as a neuron topology map, based on the grid method combined with the bio-inspired neural network. Then a new 3D dynamic movement model for multi-robots is established based on an improved Dragonfly Algorithm (DA). Thus, the movements of the robots are optimized according to the activities of the neurons in the bio-inspired neural network to realize the real-time path planning. Furthermore, some simulations have been carried out. The results show that the proposed method can effectively guide the heterogeneous UAV/UGV system to the target, and has better performance than traditional methods in the real-time path planning tasks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据