The human labor required for tree crop harvesting is a major cost component in fruit production and is increasing. To address this, many existing research works have sought to demonstrate commercially viable robotic harvesting for tree crops, though successful commercial products resulting from these have been few and far between. Systems developed for specific crops such as sweet peppers or apples have shown promise, but the vast majority of cultivar types remain unaddressed, and developing a specific system for each one is inefficient. In this study, an easily modifiable development platform for robotic fruit harvesting is presented, this can be used to test specific design choices on different fruit and growing conditions. The system is evaluated in a commercial plum orchard, with no crop modifications. Both a hard and soft gripper are trialed, along with three object detector approaches and two picking motions. Some existing techniques are found to be counterproductive for plums, while soft robotics and persistent target tracking significantly improve performance. The best harvest success rate of 42%, was observed when using the soft gripper with complex motion. This is lower than expected based on prior testing with apples and indicates the difficulty in moving to new fruit types. Unique challenges specific to the plum type and growing style are examined in the context of system module design choices.

No abstract

No abstract