Sbir phase II: precision weeder

Harvest Moon Automation Inc. received a $1.23M Cooperative Agreement from the National Science Foundation (NSF) Technology, Innovation, and Partnerships (TIP) program (CFDA 47.084), awarded July 1, 2025, with completion targeted for June 30, 2027. This Small Business Innovation Research (SBIR) Phase II project delivers the development, construction, and field testing of an automated precision weeder designed to eliminate weeds without chemical herbicides or soil tillage. The solution leverages advances in machine vision and artificial intelligence (AI) control technologies to identify individual plants within agricultural fields, distinguish crops from weeds, and selectively remove weeds with minimal disruption to neighboring plants and soil. Rigorous testing will be conducted at customer farm locations to validate prototype performance across both large and small commercial farming operations.

The automated weeder addresses critical agricultural industry challenges by providing a cost-effective, environmentally sustainable alternative to current weed management practices. By eliminating the need for herbicide application and mechanical soil tillage—both of which degrade soil microbial health and pose worker safety concerns—this technology promotes soil sustainability while reducing chemical exposure in the food supply. The project builds upon successful completion of an SBIR Phase I grant ($250,665 in 2022) and represents a strategic investment in precision agricultural automation that aligns with NSF TIP's focus on translating research innovation into practical solutions for national challenges.

Abstract

The broader/commercial impact of this small business innovation research (sbir) phase II project is that IT will result in the development of an automated weeder that can remove weeds without using chemicals or soil tillage. The two common methods of weed control in the agricultural industry, herbicides and soil tillage, have a negative impact on the environment and soil sustainability. The health of the microbial environment in the soil is degraded by the use of herbicides and soil tillage. In addition, herbicides have a negative impact on the food supply and the agricultural workers who apply them. At this time, the only option for weed control of mid-to-late-stage weeds without the use of herbicides or soil tillage is manual labor, which is more expensive. The successful development and testing of the automated weeder will provide the agricultural industry with a cost-effective solution for weed control that promotes soil sustainability, reduces chemical use in the food supply, and safeguards the health of agricultural workers. This small business innovation research (sbir) phase II project involves the development of an automated weeder that will remove weeds for large and small commercial farms. Advances in machine vision have made IT possible to identify the individual plants in a field and determine which plant is the crop and which one is the weed. Similar to hand weeding, the automated weeder will eliminate each individual weed. The novel design of the weeder will enable IT to precisely eliminate each weed with minimal disruption to neighboring plants and soil. Advances in AI control and design will create a smart weeder that will efficiently eliminate the weed based upon the type of weed and its proximity to the crop. The proposed r & d plan will result in the development, build, and testing of the prototype automated weeder. Rigorous testing will be conducted in the customers? Fields to evaluate the prototype performance with actual crops and weeds. The control software and design will be optimized based upon the field test results. Successful field trials will demonstrate that the automated weeder is a viable option for commercial automated weeding. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are planned for this award.