The AlphaGarden is an automated testbed for indoor polyculture farming which combines a first-order plant simulator, a gantry robot, a seed planting algorithm, plant phenotyping and tracking algorithms, irrigation sensors and algorithms, and custom pruning tools and algorithms.

AlphaGardenSim is a custom, fast, polyculture garden simulator which was used to learn various planting, irrigation, and pruning policies which were later evaluated in real.

Using an overhead camera and soil sensors to collect data from a physical scale garden testbed, the autonomous system utilizes a learned Plant Phenotyping convolutional neural network and a Bounding Disk Tracking algorithm to evaluate the individual plant distribution and estimate the state of the garden each day. From this garden state, AlphaGardenSim selects plants to autonomously prune and how much to irrigate each plant. A trained neural network detects and targets specific prune points on the plant.

The pruning pipeline is experimentally evaluated through four controlled 60-day garden cycles. Results suggest the system can autonomously achieve 0.94 normalized plant diversity with pruning shears while maintaining an average canopy coverage of 0.84.

Last, this thesis systematically compares the performance of the AlphaGarden to professional horticulturalists on the staff of the UC Berkeley Oxford Tract Greenhouse, adding closed loop variable irrigation. The humans and the machine tend side-by-side polyculture gardens with the same seed arrangement. We compare performance in terms of canopy coverage, plant diversity, and water consumption. Results from four 60-day cycles suggest that the automated AlphaGarden performs comparably to professional horticulturalists in terms of coverage and diversity, and reduces water consumption by as much as 44%.




Download Full History