There are some jobs human bodies just weren’t meant to do. Unloading trucks and shipping containers is a repetitive, grueling task — and an enormous reason warehouse injury rates are greater than twice the national average.
The Pickle Robot Company wants its machines to do the heavy lifting. The corporate’s one-armed robots autonomously unload trailers, picking up boxes weighing as much as 50 kilos and placing them onto onboard conveyor belts for warehouses of all sorts.
The corporate name, an homage to The Apple Computer Company, hints on the ambitions of founders AJ Meyer ’09, Ariana Eisenstein ’15, SM ’16, and Dan Paluska ’97, SM ’00. The founders intend to make the corporate the technology leader for supply chain automation.
The corporate’s unloading robots mix generative AI and machine-learning algorithms with sensors, cameras, and machine-vision software to navigate latest environments on day one and improve performance over time. Much of the corporate’s hardware is customized from industrial partners. You might recognize the arm, for example, from automobile manufacturing lines — though you could not have seen it in shiny pickle-green.
The corporate is already working with customers like UPS, Ryobi Tools, and Yusen Logistics to take a load off warehouse employees, freeing them to resolve other supply chain bottlenecks in the method.
“Humans are really good edge-case problem solvers, and robots will not be,” Paluska says. “How can the robot, which is admittedly good on the brute force, repetitive tasks, interact with humans to resolve more problems? Human bodies and minds are so adaptable, the best way we sense and reply to the environment is so adaptable, and robots aren’t going to interchange that anytime soon. But there’s a lot drudgery we are able to eliminate.”
Finding problems for robots
Meyer and Eisenstein majored in computer science and electrical engineering at MIT, but they didn’t work together until after graduation, when Meyer began the technology consultancy Leaf Labs, which focuses on constructing embedded computer systems for things like robots, cars, and satellites.
“A bunch of friends from MIT ran that shop,” Meyer recalls, noting it’s still running today. “Ari worked there, Dan consulted there, and we worked on some big projects. We were the first software and digital design team behind Project Ara, a smartphone for Google, and we worked on a bunch of interesting government projects. It was really a way of life company for MIT kids. But 10 years go by, and we thought, ‘We didn’t get into this to do consulting. We got into this to do robots.’”
When Meyer graduated in 2009, problems like robot dexterity seemed insurmountable. By 2018, the rise of algorithmic approaches like neural networks had brought huge advances to robotic manipulation and navigation.
To work out what problem to resolve with robots, the founders talked to people in industries as diverse as agriculture, food prep, and hospitality. In some unspecified time in the future, they began visiting logistics warehouses, bringing a stopwatch to see how long it took employees to finish different tasks.
“In 2018, we went to a UPS warehouse and watched 15 guys unloading trucks during a winter night shift,” Meyer recalls. “We spoke to everyone, and never a single person had worked there for greater than 90 days. We asked, ‘Why not?’ They laughed at us. They said, ‘Have you ever tried to do that job before?’”
It seems warehouse turnover is certainly one of the industry’s biggest problems, limiting productivity as managers consistently grapple with hiring, onboarding, and training.
The founders raised a seed funding round and built robots that might sort boxes since it was a better problem that allowed them to work with technology like grippers and barcode scanners. Their robots eventually worked, but the corporate wasn’t growing fast enough to be profitable. Worse yet, the founders were having trouble raising money.
“We were desperately low on funds,” Meyer recalls. “So we thought, ‘Why spend our last dollar on a warm-up task?’”
With money dwindling, the founders built a proof-of-concept robot that might unload trucks reliably for about 20 seconds at a time and posted a video of it on YouTube. A whole lot of potential customers reached out. The interest was enough to get investors back on board to maintain the corporate alive.
The corporate piloted its first unloading system for a 12 months with a customer within the desert of California, sparing human employees from unloading shipping containers that may reach temperatures as much as 130 degrees in the summertime. It has since scaled deployments with multiple customers and gained traction amongst third-party logistics centers across the U.S.
The corporate’s robotic arm is made by the German industrial robotics giant KUKA. The robots are mounted on a custom mobile base with an onboard computing systems so that they can navigate to docks and adjust their positions inside trailers autonomously while lifting. The top of every arm includes a suction gripper that adheres to packages and moves them to the onboard conveyor belt.
The corporate’s robots can pick up boxes ranging in size from 5-inch cubes to 24-by-30 inch boxes. The robots can unload anywhere from 400 to 1,500 cases per hour depending on size and weight. The corporate high quality tunes pre-trained generative AI models and uses various smaller models to make sure the robot runs easily in every setting.
The corporate can also be developing a software platform it may well integrate with third-party hardware, from humanoid robots to autonomous forklifts.
“Our immediate product roadmap is load and unload,” Meyer says. “But we’re also hoping to attach these third-party platforms. Other firms are also attempting to connect robots. What does it mean for the robot unloading a truck to confer with the robot palletizing, or for the forklift to confer with the inventory drone? Can they do the job faster? I believe there’s an enormous network coming by which we want to orchestrate the robots and the automation across the complete supply chain, from the mines to the factories to your front door.”
“Why not us?”
The Pickle Robot Company employs about 130 people in its office in Charlestown, Massachusetts, where a normal — if green — office gives option to a warehouse where its robots might be seen loading boxes onto conveyor belts alongside human employees and manufacturing lines.
This summer, Pickle will probably be ramping up production of a new edition of its system, with further plans to start designing a two-armed robot sometime after that.
“My supervisor at Leaf Labs once told me ‘Nobody knows what they’re doing, so why not us?’” Eisenstein says. “I carry that with me on a regular basis. I’ve been very lucky to find a way to work with so many talented, experienced people in my profession. All of them bring their very own skill sets and understanding. That’s an enormous opportunity — and it’s the one way something as hard as what we’re doing goes to work.”
Moving forward, the corporate sees many other robot-shaped problems for its machines.
“We didn’t start out by saying, ‘Let’s load and unload a truck,’” Meyers says. “We said, ‘What does it take to make an important robot business?’ Unloading trucks is the primary chapter. Now we’ve built a platform to make the subsequent robot that helps with more jobs, starting in logistics but then ultimately in manufacturing, retail, and hopefully the complete supply chain.”