• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer
  • Skip to navigation
Close Ad

The Spoon

Daily news and analysis about the food tech revolution

  • Home
  • Podcasts
  • Events
  • Newsletter
  • Connect
    • Custom Events
    • Slack
    • RSS
    • Send us a Tip
  • Advertise
  • Consulting
  • About
The Spoon
  • Home
  • Podcasts
  • Newsletter
  • Events
  • Advertise
  • About

agriculture

July 8, 2019

Vegebot Can Identify and Harvest Lettuce (and More, at Some Point)

Homer Simpson once sang “You don’t win friends with salad,” but he might change his tune if he knew those greens were harvested by a robot.

Well, probably not. But we at The Spoon definitely think its cool that researchers at the University of Cambridge in England have developed a robot that can automatically identify and harvest heads of iceberg lettuce. Dubbed “Vegebot,” the research team announced over the weekend that its robot had successfully completed tests in a variety of field conditions on an actual farm.

Because it grows flat to the ground and is easily damaged, iceberg lettuce can be a challenging crop to harvest. The Vegebot uses an on-board camera and computer vision to identify the lettuce, whether it is mature enough to be harvested, and if it is healthy (diseased lettuce could spread to other lettuce in the harvest). Once identified, a second camera near the cutting blade makes sure the cut is smooth before a robot gripper picks it up.

This high-tech harvesting is cool, but as of now, it is also very slow. You can see just how slow in this video:

Robot uses machine learning to harvest lettuce

However, like with most things robotic, the speed will come. Right now, the robot has proven that its computer vision, cutting and gripping technology can work outside of the lab and under a variety of conditions. Additionally, the robot’s name is “Vegebot” not “Lettucebot” (there already was one of those), and Cambridge researchers say that the underlying technology could be used for a variety of crops.

Automation and robots are on the verge of becoming more mainstream in agriculture as technology like Vegebot’s, Augean Robotics and Agerris improve, and human labor shortages become more of an issue. Working on a farm requires intense physical labor, often in 100-plus degree weather. Having robots on hand can mean continued production without risking human life and health.

Even Homer Simpson can see that’s a winning idea.

March 5, 2019

IBM to Use IoT, Watson and Data to Boost Sugar Cane Production in Thailand

If you’re around my age, when you think of IBM, an image of big mainframe computers with giant rotating tape loops come to mind (I’m old). But for you young’uns, you’d be forgiven if the first thing that comes to mind when thinking about IBM is food.

Today, Big Blue announced a two-year research collaboration with the Thailand government’s National Science and Technology Development Agency (NSTDA) that will use IBM’s Internet of Things (Iot), artificial intelligence (AI) and analytics capabilities to help improve sugarcane yields in Thailand. (Thailand is the world’s second largest exporter of sugar.) The pilot will run on three sugar cane farms covering 1 million square meters run by Mitr Phol, Asia’s largest sugar producer.

IBM’s Agronomic Insights Assistant will bring together elements of IBM Watson Decision Platform for Agriculture, the IBM Pairs Geoscope and The Weather Company, which IBM purchased in 2015. The program will gather data from the fields (soil moisture, crop health, etc.) using a combination of IoT sensors and satellite imagery, which will be augmented with local data from the NSTDA and years of weather data from The Weather Company to better predict potential environmental issues like rainfall.

The IBM platform will then take all this data and run it through Watson to create a software and mobile dashboard to help Mitr Phol better assess and manage risks like pests, diseases, irrigation and pesticide/fertilizer application, with the goal of optimizing productivity and increasing crop yield.

The Agronomic Insights Assistant will start its pilot in the middle of this year, and because IBM is working with NSTDA, a government agency, the insights gained may be shared with other farmers in the region so they can apply the same tactics.

As noted earlier, IBM is a name that keeps popping up in the food tech space for us here at The Spoon. In September of last year the company created the Agropad, a cheap, paper sensor that could be used to measure acidity and chemical levels in soil. And earlier this year, Big Blue partnered with McCormick to apply its AI tech to developing new spices.

Right now, the Agronomic Insights Assistant is in the research phase, so things like pricing and availability weren’t discussed. IBM is facing a lot of competition in the data-driven-insights-for-agtech space. Arable and Teralytic both make field sensors to provide data on soil conditions, Taranis uses aerial imaging including from satellites to help farmers spot diseases early, and Hi Fidelity Genetics uses sensors, data and AI for improved crop breeding.

The advantage IBM has, of course, is that it’s IBM. It has existing sales channels, Watson is perhaps the premiere AI brand, and it can combine sensors, data, weather prediction and AI under one roof. And, of course, a younger generation of farmers unfamiliar with IBM’s roots may not have the preconceived notion of IBM’s mainframe roots.

April 15, 2018

3 Low-Tech Solutions That Could Impact a High-Tech Food Industry

Innovative food-related gadgets and practices don’t always have to rely on things like sensors, apps, and machine learning to have a positive impact. In fact, in some parts of the world, these “low-tech” (that is, technologically simple) solutions are often all that’s needed to prevent waste, improve farming practices, and even boost the local economy.

That is to say that low tech, while maybe not as alluring as, say, using sensors to save the bees, plays a bigger role in advancing food than one might initially think. Their simplicity is effective, and often just as interesting, or at least thought provoking, as a high-tech alternative.

Consider fermentation, specifically as a way to curb food waste. Instead of just chucking food that’s about to decay (or selling it at a discount on a digital marketplace), some countries turn to a kind of “controlled decay” through fermentation. This isn’t new. The idea of preservation through decay has been around for thousands of years. And around the world, it’s still a food preservation practice.

This post gives a pretty good rundown of some of the delicacies you can find in Vietnam that exist due to preserving food through fermentation, including rượu nếp, which many Vietnamese believe kills parasites. There’s also fish sauce — the kind you’ll find on restaurant menus anywhere in the world — as well as kimchi, Sauerkraut, and Filmjölk, to name a few. True fermentation connoisseurs, I dare you to try this.

Fermentation honestly seems like kind of a no-brainer in terms of a way for, say, restaurants to preserve food and reduce waste. It’s already a trend amongst foodies, which makes me wonder if, as more and more people make efforts to curb waste, fermentation has a chance to go from delicacy to staple.

Speaking of food spoilage: typically, the closer one gets to the Equator, the faster food decays. So it makes unfortunate sense that in Kenya, fruit and vegetable vendors are constantly losing money because their produce goes bad after only a couple days. The same is true for many places of similar latitude where refrigeration isn’t always readily available.

A company called FreshBox (not to be confused with hydroponic produce company FreshBox Farms) came up with a pretty simple solution: a solar-powered cooling unit — the “box” — that looks a bit like a walk-in fridge, but reportedly costs way less to operate. Each unit can hold 70 crates of produce. Vendors pay 70 Kenyan shillings ($.068) per crate per day.

Food waste is one of the main contributors to millions of people in Africa facing starvation. According to the Rockefeller Foundation, 50 percent of all produce is lost in the post-harvest stage of production. FreshBox may not be able to solve such a massive problem overnight, but it’s proof that serious problems don’t always require a high-tech answer. Sometimes a cold box powered with cheap solar energy will do.

Another pervasive problem the food industry faces is scarcity of arable land. An oft-quoted figure is that by 2050 we’ll have to feed 2 billion more people worldwide. But it’s also generally agreed on that farmers will have to produce more food on less land. Indoor farms that raise plants without soil are one solution, but there’s no proof yet that these “modern” farming systems will be enough.

And some haven’t given up on traditional agriculture land yet. Regenerative agriculture is a land-management strategy that restores soil fertility and resilience and, in the process, sequesters CO2 emissions to mitigate climate change. Like fermentation, practices in regenerative agriculture have been around almost since the dawn of agriculture itself. They include everything from crop rotation, low tillage, installing cover crops, planting borders for bee habitats, and composting, to name a few.

One especially interesting aspect of regenerative agriculture is the role livestock can play — a definite counterpoint to the idea that livestock production is only harming the planet. Some farmers have taken to a practice called “rotational grazing,” where livestock is strategically moved around to graze, so no one part of the land is entirely depleted.

Some farmers and ranchers are already exploring the possibilities of how this seemingly low-tech action could integrate with various high-tech components in order to mitigate the burden of livestock production while also helping the actual soil. And more software is becoming readily available when it comes to overall land management, so it will be interesting to see if it can work in tandem with these age-old farming methods.

A lot of these “low-tech” innovations are currently happening in the developing world, more as a necessity than for some “oh cool” factor. At the risk of over-simplifying the matter, it would be worthwhile for food companies in more developed nations to explore these practices in more detail. Would, for example, something like FreshBox be of use to those at farmer’s markets, or the fruit and vegetable vendors who set up on the streets here in NYC? Could restaurants make more use of fermentation instead of throwing out huge percentages of their inventory?

Doing so would obviously require a lot more effort than just casual interest or enthusiasm. Still, it would behoove us to step away from the burger-flipping robots for a sec and explore such possibilities.

 

April 10, 2018

Nectar Puts Sensors in Hives to Help Save the Bees

Mark Wahlberg knows it. Debbie Harry knows it. And you probably know it too. Bee populations are declining, and that is bad news.

According to the USDA, “One out of every three bites of food in the United States depends on honey bees and other pollinators. Honey bees pollinate $15 billion worth of crops each year, including more than 130 fruits and vegetables.” But since 2006, roughly 30 percent of beehives have collapsed due to disease, pesticides and loss of habitat.

The good news, however, is that a Canadian startup called Nectar is using technology to help beekeepers better manage their colonies to help fight off this decline. The company creates sensors (also called Nectar) that go directly into beehives to monitor data such as temperature, humidity, and weight of the hive as well as the frequencies the bees emit.

Up to three sensors can be placed in a hive, depending on the type of data and how much of it you want to collect. For instance, one can be placed in the brood to monitor bee activity, or you can add more to get an overall sense of the hive and its honey production. Each sensor uses Bluetooth, which, according to the company’s lead apicultural scientist, won’t harm the bees. Readings are broadcast from the sensors to a nearby gateway every hour, and then the data is transmitted to the Cloud.

Nectar then parses through all that information and transmits it to a dashboard that keeps the beekeeper updated on the state of their bees. They can quickly learn if a new queen is hatching, whether the temperature in the hive is ideal, if there are parasites in the hive, or when the bees are about to swarm (when roughly half of the colony splits off to create a new hive).

Nectar wants to modernize beekeeping, which hasn’t changed its traditional methods for the past 100 years. Those traditional methods are manual and disruptive, with beekeepers physically opening up hives each week to check in on them, which agitates the bees and reduces their honey production. Once inside the hive, beekeepers usually rely on inaccurate, “gut” reactions to the look, sound and smell to determine its overall health.

According to Nectar co-Founder Marc-André Roberge, the result of adding his company’s sensors is farmers “Cutting down on operating cost. Losing fewer hives and raising revenue in terms of honey production and pollination contracts.”

Nectar was part of the Founder Fuel accelerator’s 2017 cohort, which gave the company $100,000 (Canadian). Nectar sensors are in pilot programs right now with commercial beekeepers, and the company aims to officially launch the first version of their product in Q1 of 2019 (when the new bee season starts). It will cost $2.50 ($1.98 USD) per month for one sensor, $4.00 ($3.17 USD) for two sensors, and $5.50 ($4.37 USD) for three sensors.

Nectar’s homepage says it can “Give your bees a voice.” Hopefully, people will listen.

March 8, 2018

Augean Robotics’ Autonomous “Burro” Follows Farm Workers to Haul Stuff

As Augean Robotics Co-Founder and CEO Charles Andersen explains it, when you work on a farm, you do a lot of high dexterity activity—like picking fruit. But you also spend a lot of time just running stuff like harvested fruit or equipment back and forth. He should know: Anderson grew up on a 100-plus acre farm in Pennsylvania.

To help with the repetitive drudgery of hauling items to and fro, Andersen’s company has developed Burro, an autonomous, rugged cart robot that can follow a person around and haul things for them.

The Burro has a 26-inch by 48-inch chassis and comes with a two-wheel and a four-wheel drive option. The two-wheel Burro can carry 300 pounds and the four-wheel drive up to 450 pounds. Burros are powered by sealed lead acid batteries, have a top speed of five miles per hour, and can travel up to 15 miles on a charge.

Using sensors and machine learning algorithms, the Burro can lock on to you as you approach it. From there it will follow you around without the need for you to hold a remote or a beacon. Its following capability, however, isn’t perfect. It can be likened to a dog; if someone else walks in between you and the Burro, it can get distracted. It will stop and wait for you to come back, or for someone else to come within its range.

The Burro can also create an automated route by following a person. For example, if blueberries are being harvested, it can follow a farmer who walks around a particular row of plants. The Burro then learns this route and can go around on its own. Each picker on that row can then set their harvested baskets of berries on the Burro as it passes by on its route.

The goal is to create a robot that collaborates with, rather than replaces, human workers. Farm workers can stick to high dexterity tasks like picking fruit while the nimble Burro navigates its way around people and crops to move stuff around where it needs to go. To achieve that, Andersen wants to keep Burro small, so farms can have many of them just running around all the time carrying fruit, tools, or whatever needs to be moved.

Each Burro costs between $9,000 and $10,000, though Andersen says that half of that cost goes towards one sensor that’s key to making the robot autonomous. He claims the price of that should come down in the future, making Burros a lot less expensive. Augean’s ultimate plan is to make the Burro a platform, and offer expansion kits that allow the robot to do more tasks.

Based in Phoenixville, PA, Augean is currently bootstrapped and has five people working on the product. It uses Anderson’s 191 acre farm for testing purposes, and hopes to have field trials with big growers this summer.

If it takes off, farmhands could soon get a big hand from a bunch of small robots.

Previous

Primary Sidebar

Footer

  • About
  • Sponsor the Spoon
  • The Spoon Events
  • Spoon Plus

© 2016–2025 The Spoon. All rights reserved.

  • Facebook
  • Instagram
  • LinkedIn
  • RSS
  • Twitter
  • YouTube
 

Loading Comments...