Precision fruit tree pruning using a learned hybrid vision/interaction controller

Abstract

Robotic tree pruning requires highly precise manipulator control in order to accurately align a cutting implement with the desired pruning point at the correct angle. Simultaneously, the robot must avoid applying excessive force to rigid parts of the environment such as trees, support posts, and wires. In this paper, we propose a hybrid control system that uses a learned vision-based controller to initially align the cutter with the desired pruning point, taking in images of the environment and outputting control actions. This controller is trained entirely in simulation, but transfers easily to real trees via a neural network which transforms raw images into a simplified, segmented representation. Once contact is established, the system hands over control to an interaction controller that guides the cutter pivot point to the branch while minimizing interaction forces. With this simple, yet novel, approach we demonstrate an improvement of over 30 percentage points in accuracy over a baseline controller that uses camera depth data.

Literature study on robotic tree harvesting and pruning : The Next Fruit 4.0 - Multifunctional robot deliverable 1

“…In (Ma et al, 2021), SPGNet model was used to realize 3D segmentation of Trunk and Branch from the point cloud. As an example of another 2D-based method, the simulation method utilizing reinforcement learning with 2D images is interesting (You et al, 2021). Through 2D-based reinforcement learning in the simulation domain, pruning behavior of robot arm and end effector can be learned without directly dealing with 3D models.…”