Font Size: a A A

A robotic and vision system for locating and transferring container-grown tobacco seedling

Posted on:1992-06-19Degree:Ph.DType:Dissertation
University:North Carolina State UniversityCandidate:Lee, Dae-WeonFull Text:PDF
GTID:1478390014499255Subject:Engineering
Abstract/Summary:
Germination and early growth of tobacco seedlings in trays containing many cells is increasing in popularity. Since 100% germination is not likely, a major problem is to locate and replace the content of those cells which contain either no seedling or a stunted seedling with a plug containing a viable seedling. Empty cells and seedlings of poor quality take up valuable space in a greenhouse. They may also cause difficulty when transplanting seedlings into the field. Robotic technology, including the implementation of computer vision, appears to be an attractive alternative to the use of manual labor for accomplishing this task. Operating AGBOT, short for AGricultural roBOT, involved four steps: (1) capturing the image, (2) processing the image (3) moving the manipulator and (4) working the gripper.; The objective of this research was to design and construct a robotic system specifically tailored to transfer seedlings within a cell-grown environment. The configuration of the cell-grown seedling environment dictated the design of a Cartesian robot suitable for working over a flat plane. Transfer of seedlings pointed to the design of two end effectors: (1) a four-spade gripper intended to pick up seedlings growing in a soil medium requiring support from four sides during transfers and (2) a single-needle end effector which was suited to the transfer of fiber growing media, like rockwool, requiring no side support. Finally, the system was to have integrated vision for detecting the quality of plants within each cell in order for the computer to furnish transfer instructions to the robot.; In all tests of small and medium sized seedings, the success rate for plant detection of imaging spectroscopy was 100%. Experiments of AGBOT performance in transferring large seedlings produced trays which were more than 98% full. Of the seedlings which were transferred, more than 95% survived one week after transfer. In general, the system generated much better than expected and work is planned to implement refinements for other applications.
Keywords/Search Tags:Transfer, System, Seedling, Robotic, Vision
Related items