Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
A sim-trained hybrid RL policy prunes planar orchard trees and transfers zero-shot to real trials.
Researchers present a closed-loop visuomotor controller for pruning planar V-Trellis apple and UFO cherry orchards. The policy is trained entirely in simulation with synthetic meshes, motion-planned demonstrations, and a hybrid reinforcement-learning method combining offline demos and online rollouts. Across 3,000 simulated cut points it reaches 49.9% success on apples and 46.0% on cherries. Zero-shot transfer is shown in 38 physical trials, and the policy beats RRT-Connect in laboratory tests.
- Controller trains only in simulation and transfers zero-shot to orchards.
- Optical flow from a wrist camera avoids full 3D reconstruction.
- Simulated success is 49.9% on apples and 46.0% on cherries.
- Thirty-eight physical trials include 28 outdoor orchard tests.
Full article221 words · extracted from arxiv.org · click to collapse
Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In this work, we focus on pruning of modern planar tree training systems - V-Trellis apples and UFO cherries - where trunks and primary branches are trained into approximately planar walls. We introduce an end-to-end pipeline to learn a closed-loop visuomotor controller for robotic pruning. This controller is trained entirely using simulation and synthetically generated data and deployed in real orchards in a zero-shot manner. The pipeline comprises synthetic generation of planar orchard tree meshes, construction of a physics-based orchard simulator, automated collection of successful pruning trajectories via motion planning, and policy learning with a novel hybrid reinforcement-learning algorithm that combines offline demonstrations with online simulated rollouts. The controller uses optical-flow inputs from a wrist-mounted camera - avoiding the need for full 3D-reconstruction - and continuously guides the cutter through cluttered branch environments to a specified cutpoint with correct tool orientation. In exhaustive simulated task-space evaluations over 3,000 pruning points, the policy attains 49.9% success on V-Trellis apples and 46.0% on UFO cherries. We validate the learned controller across 38 physical trials - comprising 28 outdoor field trials in commercial and experimental orchards and 10 indoor laboratory tests - demonstrating zero-shot sim-to-real transfer. The learned policy also outperforms a classical RRT-Connect baseline on physical hardware in laboratory trials.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.24906