|
Ji Shouwen
Li Keqiang
Miao Lixin
Modern Logistics Research Center
of Shenzhen Graduate School,
Tsinghua University,
Shenzhen 518057, China
Wang Rongben
Guo Keyou
Transportation College,
Jilin University,
Changchun 130025, China
|
|
|
DESIGN OF A NEW TYPE OF AGV BASED ON COMPUTER VISION*
Abstract:
The structure, function and working principle of JLUIV-3, which is a new type of automated guided vehicle (AGV) with computer vision, is described. The white stripe line with certain width is used as inductive mark for JLUIV-3 automated navigation. JULIV-3 can automatically recognize the Arabic numeral codes which mark the multi-branch paths and multi-operation buffers, and autonomously select the correct path for destination. Compared with the traditional AGV, it has much more navigation flexibility and less cost, and provides higher-level intelligence. The identification method of navigation path by using neural network and the optimal control method of the AGV are introduced in detail.
Key words: AGV Computer vision Optimum control Path identification Logistics |