Combination of unique gripper designs with AI and machine vision

Founded by MIT graduates, RightHand Robotics has developed a more reliable and adaptable order picking robot in a warehouse environment.

For most people, it is easy to identify an object, pick it up, and relocate it. For robots, you need the latest machine intelligence and robot operation.

This is what MIT’s spin-off RightHand Robotics has integrated into the robot’s piece removal system. The system combines a unique gripper design with artificial intelligence and machine vision to support companies in product classification and order placement.

“If you want to buy something in-store, slide the shopping cart down the aisle and choose for yourself. Ordering online works the same way in the fulfillment center,” says Lael Odhner, co-founder of RightHand Robotics. ’04, SM ’06, PhD ’09. “Retailers typically need to pick, scan, or place a single item in a sorter or conveyor belt to complete an order. Tens of thousands of orders per day and 10 or 20 soccer fields. With over 100,000 unique products stocked in a large facility, it sounds easy until you imagine the estimated delivery time is ticking away. “

RightHand Robotics is helping companies respond to two big trends that have transformed retail. One was the explosive surge in e-commerce, which only accelerated during the Covid-19 pandemic. The other is the move to just-in-time inventory fulfillment. In this fulfillment, pharmacies, grocery stores, and clothing companies add to their products based on what they buy that day or week to improve efficiency.

Robot Fleet also collects data to help RightHand Robotics improve the system over time and acquire new skills such as smoother and more accurate placement. Process and performance data are sent to the company’s fleet management software. This allows customers to understand how inventory is moving through the warehouse and identify bottlenecks and quality issues.

“The idea is that e-commerce companies can change or revise the flow of operations for the entire warehouse rather than just looking at the performance of a single operation,” says Odhner. “The aim is to eliminate upstream fluctuations as much as possible and to create a simpler and leaner process.”

Go to the limit

Odner did his PhD in the laboratory of Harry Asada, a professor of Ford Engineering in the Department of Mechanical Engineering at MIT. Odner says he encouraged students to become familiar with robotics research. Colleagues also often shared their work at seminars, giving Odner a comprehensive insight into the field.

“Asada is a very well known robotics researcher, and his early work and the projects I worked on are very fundamental to what RightHand Robotics does,” said Odhner. Says.

In 2009, Odhner was a member of the winning team of the DARPA Autonomous Robotic and Manipulation Challenge. Many of the competing teams were affiliated with MIT, and the entire program was eventually led by former MIT professor Gill Pratt. After the semifinals of the MIT100K competition as “Manus Robotics” in 2013, the team was introduced to Kiva Systems founder Mick Mountz ’87 (later taken over by Amazon). Logistics.

Today, many RightHand Robotics employees and executives are from MIT. MIT researchers also explained many early customers by purchasing components invented by Odner’s team during the DARPA program.

“In general, we’re so close to MIT that it’s hard to come back,” says Odhner. “It’s kind of a family. I never leave MIT. “

At the heart of the RightHand Robotics solution is the idea of ​​using image processing and intelligent grippers to make peaceful robots more adaptable. This combination also limits the amount of training needed to operate the robot, and each machine is equipped with the hand-eye coordination of a company.

“The technical part of our job is that we have to look at unstructured presentations of consumer products and develop a meaningful understanding of them,” says Odner.

RightHand Robotics also uses an armored tool that combines suction with a new underoperated finger. This makes Odhner more flexible than robots that rely exclusively on suction cups and simple clamp grippers.

“In practice, it can help to give the hand a passive degree of freedom, a passive movement that it can perform and that it cannot actively control,” Odhner said of the robot. “They often simplify control tasks. They prevent problems from being overly restricted and make it easier to use when executing motion planning algorithms. “

The data collected by robots is also used to improve reliability over time and shed light on customers’ warehouse operations.

“We give employees an insight into their inventory, how they store their inventory and how they work both before and after picking. It can give you an insight into what you’re building, ”says Odhner. “We have very good insights into possible future problems and can give them back to our customers.”

Odhner says that warehousing could become a much larger industry if throughput improves.

“As consumers value their online shopping options more and more, more and more items need to be added to their ‘virtual’ shopping cart. The availability of people near order fulfillment centers tends to be a limiting factor in the growth of e-commerce. All of this shows a significant inefficiency in the economy, which we essentially want to address, ”says Odner. “We do the most unattractive tasks in the warehouse. For example, like the sorting instructions, we simply select something, scan it and put it on the belt for the whole day. We automate these tasks for our customers. Can take your people with them and lead them to what the customer feels more directly. “

Odhner also said more automated fulfillment centers will help protect workers’ health and safety, including ergonomic stations where goods are brought to workers for special tasks and social distance is increased. It states that it will provide for improved measures. Instead of reducing the number of employees in the warehouse, he says, “Ultimately, I want a system that plays a role like quality control and monitors robots.”

Robot easy

This year the company is announcing a third version of its picking robot. It has standardized integration and safety functions to make it easier for warehouse operators to use peace-picking robots.

“We don’t necessarily understand the extent of our advances in commercializing this autonomous system in terms of ease of integration, configuration, safety and reliability, but we have robotic systems all over the world. It’s huge because it means you can ship it right out and you can get it started and run with minimal adjustments, ”says Odhner. “There is no reason this is in a box or pallet and no one can put it up. That is our big vision. “