Orchard Automation - Dormant Pruning

To reduce labor inputs in orchards a multi-state, multi-disciplinary team is developing innovative technologies for automating pruning on apple trees.
Orchard Automation - Dormant Pruning - Articles


The goals:

  1. Formulate and evaluate rules that describe optimal pruning in terms of measurable physical attributes of canopy structure
  2. Develop 3D imaging, decision system and robot control technologies for automating dormant pruning operations in order to construct autonomous pruning systems
  3. Determine social and economic impacts of the proposed autonomous pruning system
  4. Communicate results and involve growers, industry groups, academia and students so they can adopt these technologies and incorporate the knowledge gained into their orchards, vineyards, businesses, classrooms and laboratories

Additionally it is anticipated that results may help to train human pruning crews.


Studies with tall spindle apple canopies have indicated that pruning rules may not need to be overly complicated to adequately describe optimal pruning. Preliminary results suggest that the number of primary branches emanating from the trunk may be the most important factor, while including additional detail such as secondary, tertiary or quaternary branching patterns adds considerable complexity but may not add significant benefits.

Our engineering team has invented a state-of-the-art 3D object modeling system that is capable of creating accurate 3D reconstructions of objects, even from extremely noisy laser data (Park and Kak, 2008; Park and DeSouza, 2004). Fundamental to the proposed decision system is the concept of branch junction points on a 3D reconstruction. Once we identify branch junction points, the rest of the reasoning is driven by placing coordinate frames at each such position to identify the limbs.

On-Going and Future Investigations

Research is continuing to determine the optimum severity of pruning, and these data will be used in algorithms to determine optimal pruning points. Recent advances in 3D data acquisition methods have led to inexpensive, light-weight 3D scanners for data collection. Going forward, an important goal is to use techniques of robust estimation to eliminate the errors caused by sudden motions.

A series of surveys and case studies of commercial growers in different growing areas of the United States are being conducted to determine growers' attitudes toward autonomous pruning systems and to determine the likelihood that they would adopt such technology when available. Economic analyses will be performed to determine break even points and to determine whether such systems are likely to be cost effective for growers.

Prepared by: Jim Schupp, Tara Baugher, Peter Hirst, Noha Elfiky, Johnny Park, Jayson Harper, Leland Glenna, Anouk Patel-Campillo, Julie Tarara