Washington growers founded the Washington Tree Fruit Research Commission in 1969 with a goal of developing an automated harvester, but the vision and engineering technologies necessary for such an endeavor never quite kept pace with the needs of the tree fruit industry.
Until now, perhaps. The robotic harvester under development by Abundant Robotics (read and watch “The long and tricky path to automated picking”) is able to remove apples (and pears) quickly without inflicting damage in the process. The machine is being programmed to recognize fruit size and color and to “see” fruit and pick it as the machine moves down the row.
The high potential for success means it may be time to contemplate the current and future opportunities to further automate the apple and pear industries and to begin identifying synergistic technologies or developments — such as mechanical pruning, 10-foot minimum width drive rows, the handling properties of specific varieties and the growth habits of trees.
For best results with the current version of the technology, there should be nothing between the “end effector” and the fruit; posts, tree limbs, trunks and wires all can be barriers to reach the fruit. In addition, long limbs can be sucked into the end effector, bruising and cutting the fruit that subsequently enters and passes alongside it.
To prevent damaged fruit, growers should fasten those fruiting limbs (greater than 9 inches long, greater than 10 mm in diameter or 3/8-inch caliper) to prevent them from being taken into the harvester.
Very organized canopies, where all fruiting wood is fastened to wires (or is composed of very short bourse shoots or spurs) should be compatible with robotic harvesting, regardless of whether they are vertical or angled canopies.
The very narrow canopy provides much more uniform solar radiation (heat on fruit), light distribution and fruit distribution. A much higher portion of fruit can be ready for first pick in well balanced, ultra-narrow fruiting walls.
However, random training, where only the more vertical leader is fastened to wire, is more challenging. In addition, for the robotic harvester to have the best access to fruit, wires may need to be outside the posts and the trees outside the wires, contrary to how angle canopy blocks have evolved in recent years.
Mechanical pruning appears to be a very quick and consistent method of minimizing problem wood protruding into the drive row. In the longer perspective, if the harvester can fit into 10-foot centers (plus or minus 1 to 2 feet, to be able to efficiently work in rows with variable widths of 8 to 12 feet), then vertical systems could be considered to utilize mechanical pruning, thinning and harvesting technologies.