Mechanizing Red Raspberry Canopy Management

Sponsor Agency: Washington Department of Agriculture and WRRC

Karkee, M.* (WSU team)

 

 

 

Canopy management activities such as cane pruning, bundling, and tying are labor-intensive operations in red raspberry production. Labor availability is uncertain at best and labor cost is increasing. Currently, canopy management activities are responsible for around 50% of the total production cost, which can be as high as $1,500 per acre. In addition, labor is at risk for chronic and acute injury. Mechanization has the potential to substantially reduce labor use from cane management. Through this project, we established a red raspberry plot in Prosser, WA as a test ground for evaluating various horticultural systems and mechanization solutions.

 

 

 

 

 

 

Machine Vision System for Red-Raspberry Pruning

First step in developing an automated pruning system is to distinguish one-year-old canes (called primocanes) and two-year-old canes (called floricanes), which could then be used by a robotic system to selectively remove floricanes from the mix of primocanes and floricanes. Floricanes and primocanes look similar in terms of color, shape and size of the canes during dormant season. Hence, a non-imaging spectroscopy method was investigated in this study to utilize spectral signature of primocanes and floricanes, which can vary between two types of canes based on their difference in moisture content and chlorophyll concentration. Samples of floricanes and primocanes were collected in Nov 2017 from a ‘Wakefield’ plot in Prosser, WA. Optimal wavebands were selected to distinguish primocanes and floricanes resulting in an accuracy of 91.7%. Results show a promise for developing a multispectral sensor (with a few selected bands) for distinguishing between floricane and primocane.

 

 

 

Automated Bundling and Tying of Red Raspberry Canes

Two versions of prototype mechanisms were developed and tested for automating cane bundling and tying process. Adhesive tape was used to go around the canes and tie them together. A machine vision system was developed for cane detection and localization and

was integrated with the bundling and tying mechanisms for automated operation in the field environment. The system achieved an overall success rate of 90% when tested in a red raspberry plot in Prosser, WA. We also evaluated the durability of the adhesive tapes in holding the bundled canes together, which showed that the tape used in this work was sufficiently strong to keep the bundles intact until the fruit harvesting season.