Tagalong robots follow you to learn where you go


SOURCE: ARSTECHNICA.COM
NOV 08, 2021

Burro makes carts that help growers of trees and vineyards with harvests.

When Amazon introduced its home robot Astro earlier this year, it first showcased the robot following behind a person. It's a simple idea that has captured people’s imaginations with depictions in science fiction, like R2-D2 and BB-8 from Star Wars, and in reality, with research projects like DARPA’s robotic pack mule.

Follower robots have been tapped for senseless pursuits like carrying a single bottle of water, but robots can also carry tools in a warehouse or just-picked fruit from an orchard to a packing station. Artificially intelligent machines trained to follow people or other machines can transform how we think about everyday objects, like carry-on luggage or a set of golf clubs. Now the makers of follower robots want to coordinate movement around the modern workplace.

Follower robots have been under development since the late 1990s, beginning on the ground and extending underwater and into the sky. Initial forms relied on following the location of a tag in a person’s pocket, but advances in deep learning and computer vision now allow AI to navigate by “seeing” the world through cameras and other sensors.

In farm fields, Burro offers what looks like an autonomous driving pallet on the body of a four-wheel ATV that can move freely between the rows of California fruit orchards.

To train a Burro robot, you simply press a Follow button and start walking; at the end of the path, you press the button again. Using up to 20 cameras, computer vision, and GPS, Burro follows you and memorizes the route. It can then ferry goods unassisted and communicate the path to other Burro robots.

A Burro weighs up to 500 pounds and can carry as much as 1,000 pounds. Table grape growers are using Burros to ferry fruit from laborers in vineyards to people packing the goods in clamshells before loading them onto trucks for transport to grocery stores.

Roughly 100 Burro devices are currently operating in southern California vineyards after three years of trials. The company hopes to quadruple that number with help from $10 million in new funding completed this fall.

Burro CEO Charlie Andersen says the robots have logged nearly 50,000 hours in the past five years in blueberry, blackberry, raspberry, and grape fields, as well as at plant nurseries.

Some of the new funding will go toward creating software to tackle the technical challenge of managing hundreds of rovers in the field. Burro is also working to integrate tech from Bloomfield Robotics that uses computer vision and AI to predict grape yields and monitor crops for disease or fungus. In the long run, Burro wants to provide a platform to coordinate predictive AI and machines in motion for fruit and nut orchards and vineyards.

Beyond incorporating computer vision, Burro is testing attaching robotic arms to its pallets to cut grapes from vines so a robot can harvest, prune, and de-leaf vineyards. “We are gripping and clipping, but not doing post-gripping trimming, which is immensely complex and we don’t think will be viable in commercial settings in the near term,” Andersen says.

Fruit and nut growers are increasingly incorporating computer vision into their work. Tastry, for example, uses AI to look for combinations of grapes that can mask smoky flavors at vineyards tainted by wildfires, and a cross-disciplinary team of biologists and AI researchers working with the US Department of Agriculture is seeking ways to protect vineyards from fungus that can spoil a crop.

Walt Duflock helps run a 10,000-acre farm in California’s Monterey County for cattle, table grapes, and other crops. He’s also VP of innovation for the Western Growers Association, a consortium of farmers that represents half of the fruit-, vegetable-, and nut-growing operations in the US.

Duflock first met Burro’s founders while working as a mentor for the Thrive agriculture startup accelerator. He thinks automation is necessary to address labor shortages in agriculture, particularly for harvesting. Over time, he thinks robots like Burro can eliminate up to 20 percent of labor on farms.

That’s particularly important as the pool of potential farm workers shrinks. Rural populations are declining, and farm workers are aging, according to the Census. American Community Survey data shows the average farm worker was 39.5 in 2019, up from 35 in 2006, and the average foreign farm worker was nearly 42, since fewer young immigrants are seeking jobs in agriculture. The US Department of Labor says about two out of three workers planting fruits, vegetables, or nuts grown in the US were born in another country.

The worker issue is particularly acute on fruit and tree nut farms, where the Agriculture Department estimates labor consumes 30 percent of gross income—three times the 10 percent average for all farms.

“Burro gives them a chance to reallocate what [resources] they do have because right now there's a big gap between the labor we need and the labor we have for the ag industry,” Duflock says.

Piaggio, the maker of Vespa scooters, also sees a future in robots that can follow people. A few weeks before Amazon debuted Astro, Piaggio Fast Forward introduced GitaMini, a robot that can carry up to 40 pounds and follow you for 20 miles outdoors. Gita means short trip in Italian, and the little robot has been in development since 2015. Piaggio is advertising the GitaMini as capable of carrying a week's worth of groceries for one person living in an apartment or condo.

Beyond consumer applications, Piaggio has explored potential business use cases for follower robots. At the food delivery company Smood in Switzerland, associates fulfilling orders for customers use Gita robots to walk store aisles and then make curbside deliveries. Gita robots are also used to shop at convenience stores and gift shops and make deliveries to passengers waiting to board flights in about a dozen airports for At Your Gate.

Piaggio Fast Forward CEO Greg Lynn hopes the Mini opens more indoor uses for businesses that want to support curbside pickup and automate operations but don’t want to feel like a warehouse. “The whole world's turning into a warehouse in a funny way,” he says. “It's like everybody looks at brick and mortar and says, ‘How do I do digital fulfillment?’”

Outdoors, Lynn wants follower robots with heavy-duty tires to operate on farms and other semi-structured industrial environments. On a construction site in Colorado, the company earlier this year tested Gita robots that work as a team and follow behind a human or other robots. Theoretically, dozens or hundreds of rovers can follow each other in a platooning practice akin to fleets of autonomous trucks moving as a single train or convoy. Platoons of Gita robots deliver groceries and other items to the residents of New Haven, a planned community in Ontario, California. But platooning can raise questions about how many robot helpers is too many before they become intimidating or an unhealthy reflection of work power dynamics.

Burro’s Andersen says navigating between indoor and outdoor environments is a big challenge for follower robots. Object detection can also be an issue. When the robot encounters weeds, buckets, wheelbarrows, or other things in its path, it must decide what to drive over, what to avoid, and when to stop.

The GitaMini supplements its cameras with radar, which can be helpful when driving into sunlight or approaching the sliding glass doors common at supermarkets. Still, a person guiding a Gita down the sidewalk will have to sidestep common obstacles that the robot’s vision system has trouble identifying, such as poop and puddles. Fog, rain, snow, and other weather conditions can also impact Gita's vision systems.

And sometimes the robots get stuck. If a GitaMini robot made for indoor-outdoor travel encounters a curb or stairs it cannot overcome, you must reach down and pick up the 25-pound device. When a Burro robot fails, it can require intervention from multiple people to reset the course of a device that weighs up to 500 pounds.

“There are a lot of situationally specific things that an infant or a toddler can understand but that are incredibly difficult to make a system behave reliably around all day long, every day, without somebody having to intervene,” Andersen says.

Similar articles you can read