More stories

  • in

    Titanic robots make farming more sustainable

    There’s a lot riding on farmers’ ability to fight weeds, which can strangle crops and destroy yields. To protect crops, farmers have two options: They can spray herbicides that pollute the environment and harm human health, or they can hire more workers.

    Unfortunately, both choices are becoming less tenable. Herbicide resistance is a growing problem in crops around the world, while widespread labor shortages have hit the agricultural sector particularly hard.

    Now the startup FarmWise, co-founded by Sebastien Boyer SM ’16, is giving farmers a third option. The company has developed autonomous weeding robots that use artificial intelligence to cut out weeds while leaving crops untouched.

    The company’s first robot, fittingly called the Titan — picture a large tractor that makes use of a trailer in lieu of a driver’s seat — uses machine vision to distinguish weeds from crops including leafy greens, cauliflower, artichokes, and tomatoes while snipping weeds with sub-inch precision.

    About 15 Titans have been roaming the fields of 30 large farms in California and Arizona for the last few years, providing weeding as a service while being directed by an iPad. Last month, the company unveiled its newest robot, Vulcan, which is more lightweight and pulled by a tractor.

    “We have growing population, and we can’t expand the land or water we have, so we need to drastically increase the efficiency of the farming industry,” Boyer says. “I think AI and data are going to be major players in that journey.”

    Finding a road to impact

    Boyer came to MIT in 2014 and earned masters’ degrees in technology and policy as well as electrical engineering and computer science over the next two years.

    “What stood out is the passion that my classmates had for what they did — the drive and passion people had to change the world,” Boyer says.

    As part of his graduate work, Boyer researched machine learning and machine vision techniques, and he soon began exploring ways to apply those technologies to environmental problems. He received a small amount of funding from MIT Sandbox to further develop the idea.

    “That helped me make the decision to not take a real job,” Boyer recalls.

    Following graduation, he and FarmWise co-founder Thomas Palomares, a graduate of Stanford University whom Boyer met in his home country of France, began going to farmers’ markets, introducing themselves to small farmers and asking for tours of their farms. About one in three farmers were happy to show them around. From there they’d ask for referrals to larger farmers and service providers in the industry.

    “We realized agriculture is a large contributor of both emissions and, more broadly, to the negative impact of human activities on the environment,” Boyer says. “It also hasn’t been as disrupted by software, cloud computing, AI, and robotics as other industries. That combination really excites us.”

    Through their conversations, the founders learned herbicides are becoming less effective as weeds develop genetic resistance. The only alternative is to hire more workers, which itself was becoming more difficult for farmers.

    “Labor is extremely tight,” says Boyer, adding that bending over and weeding for 10 hours a day is one of the hardest jobs out there. “The labor supply is shrinking if not collapsing in the U.S., and it’s a worldwide trend. That has real environmental implications because of the tradeoff [between labor and herbicides].”

    The problem is especially acute for farmers of specialty crops, including many fruits, vegetables, and nuts, which grow on smaller farms than corn and soybean and each require slightly different growing practices, limiting the effectiveness of many technical and chemical solutions.

    “We don’t harvest corn by hand today, but we still harvest lettuces and nuts and apples by hand,” Boyer says.

    The Titan was built to complement field workers’ efforts to grow and maintain crops. An operator directs it using an iPad, walking alongside the machine and inspecting progress. Both the Titan and Vulcan are powered by an AI that directs hundreds of tiny blades to snip out weeds around each crop. The Vulcan is controlled directly from the tractor cab, where the operator has a touchscreen interface Boyer compares to those found in a Tesla.

    With more than 15,000 commercial hours under its belt, FarmWise hopes the data it collects can be used for more than just weeding in the near future.

    “It’s all about precision,” Boyer says. “We’re going to better understand what the plant needs and make smarter decisions for each one. That will bring us to a point where we can use the same amount of land, much less water, almost no chemicals, much less fertilizer, and still produce more food than we’re producing today. That’s the mission. That’s what excites me.”

    Weeding out farming challenges

    A customer recently told Boyer that without the Titan, he would have to switch all of his organic crops back to conventional because he couldn’t find enough workers.

    “That’s happening with a lot of customers,” Boyer says. “They have no choice but to rely on herbicides. Acres are staying organic because of our product, and conventional farms are reducing their use of herbicides.”

    Now FarmWise is expanding its database to support weeding for six to 12 new crops each year, and Boyer says adding new crops is getting easier and easier for its system.

    As early partners have sought to expand their deployments, Boyer says the only thing limiting the company’s growth is how fast it can build new robots. FarmWise’s new machines will begin being deployed later this year.

    Although the hulking Titan robots are the face of the company today, the founders hope to leverage the data they’ve collected to further improve farming operations.

    “The mission of the company is to turn AI into a tool that is as reliable and dependable as GPS is now in the farming industry,” Boyer says. “Twenty-five years ago, GPS was a very complicated technology. You had to connect to satellites and do some crazy computation to define your position. But a few companies brought GPS to a new level of reliability and simplicity. Today, every farmer in the world uses GPS. We think AI can have an even deeper impact than GPS has had on the farming industry, and we want to be the company that makes it available and easy to use for every farmer in the world.” More

  • in

    Computing for the health of the planet

    The health of the planet is one of the most important challenges facing humankind today. From climate change to unsafe levels of air and water pollution to coastal and agricultural land erosion, a number of serious challenges threaten human and ecosystem health.

    Ensuring the health and safety of our planet necessitates approaches that connect scientific, engineering, social, economic, and political aspects. New computational methods can play a critical role by providing data-driven models and solutions for cleaner air, usable water, resilient food, efficient transportation systems, better-preserved biodiversity, and sustainable sources of energy.

    The MIT Schwarzman College of Computing is committed to hiring multiple new faculty in computing for climate and the environment, as part of MIT’s plan to recruit 20 climate-focused faculty under its climate action plan. This year the college undertook searches with several departments in the schools of Engineering and Science for shared faculty in computing for health of the planet, one of the six strategic areas of inquiry identified in an MIT-wide planning process to help focus shared hiring efforts. The college also undertook searches for core computing faculty in the Department of Electrical Engineering and Computer Science (EECS).

    The searches are part of an ongoing effort by the MIT Schwarzman College of Computing to hire 50 new faculty — 25 shared with other academic departments and 25 in computer science and artificial intelligence and decision-making. The goal is to build capacity at MIT to help more deeply infuse computing and other disciplines in departments.

    Four interdisciplinary scholars were hired in these searches. They will join the MIT faculty in the coming year to engage in research and teaching that will advance physical understanding of low-carbon energy solutions, Earth-climate modeling, biodiversity monitoring and conservation, and agricultural management through high-performance computing, transformational numerical methods, and machine-learning techniques.

    “By coordinating hiring efforts with multiple departments and schools, we were able to attract a cohort of exceptional scholars in this area to MIT. Each of them is developing and using advanced computational methods and tools to help find solutions for a range of climate and environmental issues,” says Daniel Huttenlocher, dean of the MIT Schwarzman College of Computing and the Henry Warren Ellis Professor of Electrical Engineering and Computer Science. “They will also help strengthen cross-departmental ties in computing across an important, critical area for MIT and the world.”

    “These strategic hires in the area of computing for climate and the environment are an incredible opportunity for the college to deepen its academic offerings and create new opportunity for collaboration across MIT,” says Anantha P. Chandrakasan, dean of the MIT School of Engineering and the Vannevar Bush Professor of Electrical Engineering and Computer Science. “The college plays a pivotal role in MIT’s overarching effort to hire climate-focused faculty — introducing the critical role of computing to address the health of the planet through innovative research and curriculum.”

    The four new faculty members are:

    Sara Beery will join MIT as an assistant professor in the Faculty of Artificial Intelligence and Decision-Making in EECS in September 2023. Beery received her PhD in computing and mathematical sciences at Caltech in 2022, where she was advised by Pietro Perona. Her research focuses on building computer vision methods that enable global-scale environmental and biodiversity monitoring across data modalities, tackling real-world challenges including strong spatiotemporal correlations, imperfect data quality, fine-grained categories, and long-tailed distributions. She partners with nongovernmental organizations and government agencies to deploy her methods in the wild worldwide and works toward increasing the diversity and accessibility of academic research in artificial intelligence through interdisciplinary capacity building and education.

    Priya Donti will join MIT as an assistant professor in the faculties of Electrical Engineering and Artificial Intelligence and Decision-Making in EECS in academic year 2023-24. Donti recently finished her PhD in the Computer Science Department and the Department of Engineering and Public Policy at Carnegie Mellon University, co-advised by Zico Kolter and Inês Azevedo. Her work focuses on machine learning for forecasting, optimization, and control in high-renewables power grids. Specifically, her research explores methods to incorporate the physics and hard constraints associated with electric power systems into deep learning models. Donti is also co-founder and chair of Climate Change AI, a nonprofit initiative to catalyze impactful work at the intersection of climate change and machine learning that is currently running through the Cornell Tech Runway Startup Postdoc Program.

    Ericmoore Jossou will join MIT as an assistant professor in a shared position between the Department of Nuclear Science and Engineering and the faculty of electrical engineering in EECS in July 2023. He is currently an assistant scientist at the Brookhaven National Laboratory, a U.S. Department of Energy-affiliated lab that conducts research in nuclear and high energy physics, energy science and technology, environmental and bioscience, nanoscience, and national security. His research at MIT will focus on understanding the processing-structure-properties correlation of materials for nuclear energy applications through advanced experiments, multiscale simulations, and data science. Jossou obtained his PhD in mechanical engineering in 2019 from the University of Saskatchewan.

    Sherrie Wang will join MIT as an assistant professor in a shared position between the Department of Mechanical Engineering and the Institute for Data, Systems, and Society in academic year 2023-24. Wang is currently a Ciriacy-Wantrup Postdoctoral Fellow at the University of California at Berkeley, hosted by Solomon Hsiang and the Global Policy Lab. She develops machine learning for Earth observation data. Her primary application areas are improving agricultural management and forecasting climate phenomena. She obtained her PhD in computational and mathematical engineering from Stanford University in 2021, where she was advised by David Lobell. More