When Amazon introduced its home robot Astro earlier this year, it first showed the robot chasing a person. It’s a simple idea that captures the imagination with images in science fiction, such as R2-D2 and BB-8 from Star Warsand in reality, with research projects such as DARPA’s robotic pack mule.
Tracking robots have been used for pointless activities, such as 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 track humans or other machines could change the way we think about everyday objects, such as carry-on luggage or a set of golf clubs. Now the makers of tracking robots want to coordinate movement in the modern workplace.
Tracking robots have been in development since the late 1990s, starting on the ground and extending underwater and into the air. Initial forms were based on tracking 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 fields, Burro offers what appears to be an autonomously driving pallet on the body of a four-wheel ATV that can move freely between rows of California fruit orchards.
To train a Burro robot, just press a follow button and start walking; at the end of the path, press the button again. Using up to 20 cameras, computer vision and GPS, Burro tracks you and remembers the route. It can then transport goods unaided and pass 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 use Burros to transport fruit from workers in vineyards to people who pack the goods in clamshells before loading them onto trucks for transport to supermarkets.
About 100 Burro devices are currently in operation in Southern California vineyards, after three years of testing. The company hopes to quadruple that number with help from $10 million in new financing completed this fall.
Charlie Andersen, CEO of Burro, says the robots have logged nearly 50,000 hours in the past five years in fields of blueberries, blackberries, raspberries and grapes, as well as nurseries.
Some of the new funding will go toward creating software to meet the technical challenge of managing hundreds of rovers in the field. Burro is also working to integrate technology from Bloomfield Robotics that uses computer vision and AI to predict grape yields and monitor crops for diseases or fungi. In the long term, Burro aims to provide a platform to coordinate predictive AI and machines in motion for fruit and nut orchards and vineyards.
In addition to integrating computer vision, Burro is also testing attaching robotic arms to his pallets to cut grapes from vines so that a robot can harvest, prune and defoliate vineyards. “We are gripping and cutting, but not trimming after gripping, which is hugely complex and we don’t think this will be feasible in commercial environments any time soon,” Andersen says.
Fruit and nut growers are increasingly using computer vision in their work. For example, Tastry is using AI to seek out pairings of grapes that can mask smoky flavors in vineyards affected by wildfires, and a multidisciplinary team of biologists and AI researchers working with the U.S. Department of Agriculture is looking for ways to protect vineyards from fungus that can spoil a crop.
Walt Duflock helps run a 10,000-acre ranch in California’s Monterey County for livestock, table grapes and other crops. He is also VP of innovation for the Western Growers Association, a consortium of farmers that represents half of the United States’ fruit, vegetable and nut production.
Duflock first met Burro’s founders while working as a mentor for the Thrive startup accelerator for agriculture. He thinks automation is needed to address the labor shortage in agriculture, especially for harvesting. Over time, he thinks robots like Burro could eliminate up to 20 percent of farm labor.