This has the specific goal of significantly shortening the time to measure apple fruitlet growth, which will enable apple growers to manage crop load more precisely and efficiently. The technology developments used to do this will make fundamental advances in robotics and sensing for agriculture, and will take important steps toward using intelligent robots as labor saving devices in specialty crop production. The project will train graduate and undergraduate students in plant science and computer science, giving them important cross-disciplinary research experiences early in their careers. Ideas from the research project will be incorporated into a popular K-12 program that focuses on providing girls and young women with hands-on activities in robotics and agricultural science.1. Develop a 3-D camera, a robotic arm, and robot that and related software that can identify and measure fruit clusters, producing data for use in the current apple fruit thinning model MaluSim.2. Develop a cell phone application that can be used to measure fruit clusters, producing data for use in the current apple fruit thinning model MaluSim.3. Combine recent advances in 2D semantic image segmentation with 3D computer vision and mapping techniques to create robust perception systems that work in the unstructured clutter common in agricultural environments.4. Investigate the use of deep reinforcement learning approaches to solve manipulation tasks in these environments, and, specifically, it will explore the use of auxiliary reward functions to speed up the training process and transfer the result into real-world applications.5. Develop a template for development of similar imaging methods in other crop systems, solving other management problems where rapid, accurate measurement are required to more precisely manage inputs.6. Work with graduate, undergraduate and K-12 students showing the value of interdisciplinary work in agriculture and computer science.