Farm-to-Plate AI: Enhance Freshness and Reduce Waste with Robotics and Computer Vision
About This Video
Addressing global food security and reducing waste in the food supply chain are crucial challenges in today’s world. The United Nations has identified the widespread lack of access to adequate food, which is exacerbated by factors such as conflicts, pandemics, climate change, and inequality. Additionally, population growth will lead to an estimated 70% increase in the demand for food . To address these challenges and meet these growing demands, the integration of emerging technologies, particularly autonomous navigation, artificial intelligence (AI), and computer vision can help optimize farming practices, automate harvesting and grading, and monitor food quality during transportation.
A key challenge in the food supply chain is the significant amount of waste, with approximately 13% of food lost from harvesting to retail . Accurate estimation of ripeness is a crucial aspect of reducing food waste, enabling effective management of supply and demand while maximizing the utilization of available produce. In this context, the use of autonomous navigation, deep learning, and hyperspectral imaging is a promising solution.
This study presents a pipeline that showcases the transformative potential of AI and machine learning in optimizing the food supply chain and minimizing waste. We perform three experiments that focus on tracking the journey of mango fruit from a farm to plate. In the first one, we implement an autonomous navigation algorithm to simulate a UAV for capturing farm data and harvesting. Then we track the number of mangoes using object detection as they go from the harvesting stage to the warehouse. Finally, we perform concurrent monitoring of mango ripeness using machine learning on hyperspectral images [3,4].
In This Video
Senior Software Engineer, MathWorks
Shriya has presented her work at both commercial and academic venues, such as the MathWorks Advisory Board, the Mobile Computing, Applications, and Services (MobiCASE) Conference, and the Grace Hopper Celebration.
Performance Engineer, MathWorks
Dr. Nayara Aguiar is a Performance Engineer at MathWorks, focusing on benchmarking and performance analysis for Deep Learning workflows. She has also contributed to software development projects on mathematical optimization, data analysis, and applications related to the analysis of the electricity grid.
Nayara received her Ph.D. in Electrical Engineering from the University of Notre Dame, where her research interests were in the intersection of power systems, renewable energy, and economics. She volunteered in women in STEM initiatives throughout her academic career, serving as the founding chair of the IEEE Women in Engineering (IEEE WIE) student affinity group at UFCG, her alma mater in Brazil, volunteering in the Graduate Society of Women Engineers (GradSWE) Notre Dame chapter, and mentoring undergraduate students through the Association for Women in Science (AWIS) Notre Dame chapter.
Nayara has participated as a speaker and panelist in different events, such as a workshop for the 2023 Women in Data Science (WiDS) Datathon, the 2023 Grace Hopper Celebration, and multiple conferences by the Computer Measurement Group (CMG). In these events, she presented hands-on AI workshops, spoke about deep learning applications related to sustainability, and discussed green initiatives in the technology industry.
Machine Learning Engineer, MathWorks
Maitreyi works on applications of machine learning research and data engineering in the MATLAB Language and Software Foundations vertical at MathWorks. She currently works on developing AI Assisted Coding and Generative AI capabilities for MATLAB and has worked on various deep learning and computer vision projects in the past. She holds a M.S in Electrical and Computer Engineering from Carnegie Mellon University and a B.Eng in Electronics and Telecommunication Engineering from the University of Mumbai. She has also been involved in multiple workshops, organizations, and conferences such as WiML @ NeurIPS 2021, GHC, NSBE Boston, Black in AI, and CMG Impact in various capacities as a TA, volunteer, and speaker.
She has been a speaker for a workshop at GHC ’23, CMG Impact 2022, and a poster presenter for WiML@NeurIPS 2021. She has also been a moderator for socials at NeurIPS 2020 and NeurIPS 2021.
Senior Technical Consultant, MathWorks
Karthiga Mahalingam is a Senior Technical Consultant at MathWorks. She works closely with customers to design, advise, and develop technical solutions focusing in biomedical, AI, image/signal processing, and app development using MATLAB. Her previous role at MathWorks as an Application Support Engineer was also customer-facing during which she helped customers to investigate technical challenges with MATLAB especially in the domains of machine and deep learning. She holds a master’s degree in Bioengineering from Georgia Institute of Technology where her research was focused on Brain-Computer Interfaces and AI.
Karthiga has assisted the hands-on Deep Learning and IoT workshop delivery at TechTogether Boston, the largest student-led hackathon for women in Boston. She was also one of the STEM panelists at the Boston Chapter of Black Girls Code (BGC) hosted by MathWorks.
She was one of the Teaching Assistants for the “Do You See What I See: Using AR and AI” workshop presented by MathWorks at vGHC20. She was part of the speaker team for “How to Make Sense of the Unseen World” and “Farm-to-Plate AI: Enhance Freshness and Reduce Waste with Robotics and Computer Vision” Level Up Labs presented by MathWorks at GHC2022 and GHC 2023 respectively.