todo: banner-image
Year 3 Research Project
Towards Next-Generation Digital-Twin-Enabled Sustainable Large-Scale Indoor Pod Farming-Part A - Physical System, Sensors, Images, Drones and Robotics

>_

Description

Hydroponic farming is growing plants with nutrient enriched water and without soil. These mobile units can be in urban and rural settings and are seen as a solution to drought and pollution related agricultural challenges. This Year 3 Research Project builds on the team’s work from Year 2. Last year the researchers found that there is a need for indoor farming research focused on avoiding pathogens and developing models that are not region specific. For Year 3, the project will focus on developing digital-twin technologies for sustainable large-scale indoor farming, with a focus on hardware and real-world data gathering.

To understand and optimize these systems, the objective is to develop validated simulation and sensing tools to: (a) train the next generation of plant scientists, engineers and farmers to have skills in engineering, computer science & agriculture, and (b) develop innovative solutions for food security and pathogen control. This involves vertical farming panels of lettuce, herbs, hearty greens, etc., illuminated by high-efficiency LED grow lights, development of mobile software platforms which allow facility users to monitor, track and control various components in the unit. Part A specifically focuses on developing the led-driven pod-based hydroponic farming system, along with the design of sensors, cameras, drones, and robotics needed to gather data and develop models for the digital twin and consequent Performance-based Food Engineering (PBFE) simulations in Part B.

Learn more about our other indoor farming research projects.

>_

Project Video

Description

Autonomous Flight Information Collection for Indoor Pod Farming. Our project extends upon our previous work on flight simulation in agricultural environments and supports the development of a digital twin of the indoor pod environment. We constructed a dimensionally accurate 3D replica of the pod farm for cultivating Quillaja Saponaria, located at the Richmond Field Station. Our high-fidelity flight simulation showcases the vehicle's flight performance as it navigates an inspection path within the container farm. Additionally, our simulated UAV is equipped with a side-facing camera to capture synthetic visual data while in flight. These results demonstrate the feasibility of using a UAV to autonomously collect visual data for plant monitoring purposes inside the farm. With the addition of an image processing pipeline, the collected visual data could be used to detect essential plant features such as leaf growth, leaf hydration status, and mite infection indicators.

>_

Team

Portrait of Tarek Zohdi

Tarek Zohdi

Principal Investigator

Portrait of Khalid Mosalam

Khalid Mosalam

Co Principal Investigator

Portrait of Ethan Ligon

Ethan Ligon

Co Principal Investigator

Portrait of Simo Mäkiharju

Simo Mäkiharju

Co Principal Investigator

Portrait of Nitin Nitin

Nitin Nitin

Co Principal Investigator

Portrait of Francesco Borrelli

Francesco Borrelli

Co Principal Investigator

Portrait of Rebecca Abergel

Rebecca Abergel

Co Principal Investigator

Portrait of Mark Mueller

Mark Mueller

Co Principal Investigator

Portrait of Ilias Tagkopoulos

Ilias Tagkopoulos

Collaborator

>_

Publications

A thumbnail of the journal or conference cover of Safe Human-Robot Collaborative Transportation via Trust-Driven Role Adaptation
Conference Article ⏐ ACC 2023

Safe Human-Robot Collaborative Transportation Via Trust-Driven Role Adaptation

Zheng, Tony,Monimoy Bujarbaruah,Yvonne R Stürz,and Francesco Borrelli
DOI: 10.23919/ACC55779.2023.10156494