AlphaGarden: Learning to Autonomously Tend a Polyculture Garden

TL;DR

AlphaGarden is an autonomous system that manages a polyculture garden by pruning and irrigating plants using sensors, cameras, and learned policies to optimize plant diversity and coverage over multiple growth cycles.

Contribution

It introduces a novel autonomous gardening system that combines sensing, modeling, and neural network policies for plant care in a polyculture setting.

Findings

Achieved 0.96 normalized plant diversity with pruning shears

Maintained an average canopy coverage of 0.86 during peak growth

Demonstrated successful autonomous garden management over four 60-day cycles

Abstract

This paper presents AlphaGarden: an autonomous polyculture garden that prunes and irrigates living plants in a 1.5m x 3.0m physical testbed. AlphaGarden uses an overhead camera and sensors to track the plant distribution and soil moisture. We model individual plant growth and interplant dynamics to train a policy that chooses actions to maximize leaf coverage and diversity. For autonomous pruning, AlphaGarden uses two custom-designed pruning tools and a trained neural network to detect prune points. We present results for four 60-day garden cycles. Results suggest AlphaGarden can autonomously achieve 0.96 normalized diversity with pruning shears while maintaining an average canopy coverage of 0.86 during the peak of the cycle. Code, datasets, and supplemental material can be found at https://github.com/BerkeleyAutomation/AlphaGarden.