Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Research Project #445530

Research Project: Development of an Automated and Integrated Mobile System (AIMS) for Apple Harvest and In-field Sorting - Michigan State University 2

Location: Sugarbeet and Bean Research

Project Number: 5050-43640-003-015-A
Project Type: Cooperative Agreement

Start Date: Sep 15, 2023
End Date: Jul 14, 2027

1. Design and construct efficient, dexterous multi-arm robotic harvesting modules, coupled with AI algorithms and optimum systems control and planning schemes, to enable picking apples grown in high-density tree orchards. 2. Integrate multi-arm robotic modules with the mobile platform to enable selective or full harvesting of apples during day and at night. 3. Evaluate and demonstrate the multi-arm robot and Automated and Integrated Mobile System (AIMS) in diverse commercial orchard systems and with different operational strategies, in Michigan, Pennsylvania, and Washington and disseminate the technologies to growers and packers through extension and outreach activities. 4. Establish open-access repositories of labeled image data collected by multi-modal sensing systems under diverse orchard conditions as well as a performance benchmark suite of state-of- the-art AI models for fruit detection and quality grading.

Cooperator will design and construct multi-arm robotic harvesting modules for apple picking. Building upon the promising prior work, a multi-arm robot module and the corresponding perception and planning algorithms will be developed to further enhance the harvesting efficiency. Specifically, instead of using a single arm as in our existing prototype, a two-arm robotic module will be designed to achieve the multiplying effect with improved efficiency in a system that will be robust and able to perform continuous operations under various light conditions (sunny vs. overcast, day vs. night. After completion of building the two-arm robotic module, tests and evaluations will be carried out in both the simulated indoor orchard environment, with artificial trees and real apples as well as in different research and commercial orchards. Cooperator will work with ARS PI for integration of two-arm robotic modules with the mobile platform and participate with the team's extension members in field testing, evaluation and demonstration of the AIMS in Michigan, Pennsylvania and Washington. In addition, Cooperator will work with other members of the project in establishing open-access libraries on AI modules for apple detection and for collection and labeling of image data acquired using different sensors.