There are tasks for which the human body is simply not designed. Unloading trucks and containers is a repetitive, exhausting task and is the main reason why warehouse accidents are more than twice the national average.
The Pickle Robot Company wants its machines to handle the toughest jobs. The company's one-armed robots unload trailers on their own, lifting boxes weighing up to 50 pounds and placing them on onboard conveyor belts for all types of warehouses.
The company's name, an homage to The Apple Computer Company, honors the ambitions of founders AJ Meyer '09, Ariana Eisenstein '15, SM '16, and Dan Paluska '97, SM '00. The founders want to make the company a leader in supply chain automation technology.
The company's unloading robots combine generative artificial intelligence and machine learning algorithms with sensors, cameras and machine vision software to navigate new environments on day one and improve performance over time. Much of the company's equipment is adapted from industrial partners. For example, you may recognize an arm from car production lines – although you may not have seen it in light green.
The company is already working with customers such as UPS, Ryobi Tools and Yusen Logistics to reduce the burden on warehouse workers, enabling them to eliminate other bottlenecks in the supply chain.
“Humans are really good at solving edge problems, and robots are not,” Paluska says. “How can a robot that's really good at brute force and repetitive tasks interact with humans to solve more problems? Human bodies and minds are so flexible, the way we sense and respond to our environments is so flexible, and robots aren't going to replace that any time soon. But there's so much drudgery we can get rid of.”
Finding problems for robots
Meyer and Eisenstein studied computer science and electrical engineering at MIT, but didn't work together until after graduation, when Meyer founded Leaf Labs, a consulting firm that specializes in building embedded computer systems for things like robots, cars and satellites.
“A group of friends from MIT ran the store,” Meyer recalls, noting that it is still in operation today. “Ari worked there, Dan did consulting there, and we worked on some big projects. We were the core software and digital design team behind Project Ara, the smartphone for Google, and we worked on some interesting government projects. It was really a lifestyle company for MIT kids. But 10 years passed and we thought, 'We didn't get into this to consult. We set out to make robots.”
When Meyer graduated in 2009, problems like robot dexterity seemed insurmountable. By 2018, the development of algorithmic approaches such as neural networks had brought enormous advances in robotic manipulation and navigation.
To find out what problem robots could solve, the founders talked to people from industries as diverse as agriculture, food preparation and hospitality. At some point, they began visiting logistics warehouses, bringing a stopwatch with them to see how long it took employees to complete each task.
“In 2018, we went to a UPS warehouse and watched 15 employees unload trucks during the winter night shift,” Meyer recalled. “We talked to everyone and not a single person had worked there for more than 90 days. We asked, 'Why not?' They laughed at us. They asked, 'Have you tried doing this job before?'
It turns out that warehouse turnover is one of the biggest problems in the industry, limiting productivity as managers constantly struggle with recruitment, onboarding and training.
The founders raised a seed funding round and built robots that could sort boxes because it was an easier task that allowed them to work with technologies like grippers and barcode scanners. Their robots eventually worked, but the company wasn't growing fast enough to turn a profit. Worse still, the founders had trouble raising money.
“We were desperately short of funds,” Meyer recalls. “So we thought, 'Why spend our last dollar on warm-ups?'”
Facing dwindling money, the founders built a proof-of-concept robot that could reliably unload trucks for about 20 seconds at a time, and posted a video of it in action on YouTube. Hundreds of potential customers applied. There was enough interest to attract investors again and keep the company alive.
For a year, the company piloted its first on-site unloading system in the California desert, sparing workers from having to unload shipping containers that can reach temperatures of up to 130 degrees in the summer. Since then, it has expanded deployments to many customers and gained popularity among third-party fulfillment centers across the United States
The company's robotic arm is manufactured by German industrial robotics giant KUKA. The robots are mounted on a custom mobile base equipped with onboard computer systems so they can navigate to docks and independently adjust their position in trailers while lifting. At the end of each arm is a suction cup gripper that attaches to the packages and transfers them to the onboard conveyor belt.
The company's robots can lift boxes ranging in size from 5-inch cubes to 24-by-30-inch boxes. The robots can unload 400 to 1,500 cases per hour, depending on size and weight. The company fine-tunes pre-trained generative AI models and uses a series of smaller models to ensure the robot runs smoothly in every setting.
The company is also developing a software platform that can be integrated with third-party equipment, from humanoid robots to autonomous forklifts.
“Our immediate product development plan includes loading and unloading,” says Meyer. “But we're also hoping to connect third-party platforms. Other companies are also trying to connect robots. What does it mean that a robot unloading a truck is talking to a palletizing robot, or that a forklift is talking to an inventory drone? Can they do this job faster? I think there's a big network coming where we have to coordinate robots and automation across the supply chain, from mines to factories to front doors.”
“Why not us?”
The Pickle Robot Company employs about 130 people at its office in Charlestown, Massachusetts, where a standard – if green – office gives way to a warehouse where robots can be seen loading boxes onto conveyor belts alongside human workers and production lines.
This summer, Pickle will ramp up production of a new version of its system, and plans to begin designing a two-armed robot some time later.
“My manager at Leaf Labs once told me, 'No one knows what they do, so why don't we?'” Eisenstein says. “I carry that with me all the time. I've been lucky to have worked with so many talented, experienced people in my career. They all bring their own skills and understanding. It's a huge opportunity – and that's the only way something as difficult as what we do can work.”
Going forward, the company sees many other problems in the form of robots in its machines.
“We didn't start by saying, 'Let's load and unload a truck,'” Meyers says. “We said, 'What does it take to build a great robot business?' Unloading trucks is chapter one. Now we've built a platform on which we can build the next robot to help fulfill more jobs, from logistics to manufacturing, retail and hopefully the entire supply chain.”
