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.
From the original article
1 min read at arxiv.orgDormant 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.
By Abhinav Jain · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.