Combination of unique gripper designs with AI and machine vision


Righthand Robotics combines machine vision with a smart gripper design to provide a more adaptable robot.Credit: Courtesy of the researchers

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

For most people, it’s easy to identify an object, pick it up, and place it somewhere else. For robots, you need the latest technology in robot intelligence and operation.

This is what RightHand Robotics, a spin-off from MIT, integrated into the robot’s parts picking system. The system combines a unique gripping design with artificial intelligence and machine vision to help businesses categorize products and place orders.

“If you want to buy something from the store, push the cart down the aisle and choose for yourself. Ordering online does the same in the fulfillment center, ”says Lael Odhner, co-founder of RightHand Robotics. States ’04, SM ’06, PhD ’09. “Retailers typically need to pick up a single item, scan it, place it in a sorter or conveyor belt to complete an order. There are tens of thousands of orders a day and 10 or 20 football fields. With over 100,000 unique products stored in a large facility, it seems easy until you imagine the estimated delivery time is running out. “

RightHand Robotics is helping businesses respond to two megatrends that have transformed the retail industry. One of them was the explosive increase in e-commerce, which only accelerated during the Covid-19 pandemic. The other is the shift to just-in-time inventory execution. In this accomplishment, drugstores, grocery stores, and clothing companies are restocking their products based on what they buy that day or week to improve efficiency.

“We give people an overview of their inventory, information on how they store their inventory and how they operate both upstream and downstream of the picking that we do. This can give you insight into what you are building, ”says Odhner.Credit: Courtesy of the researchers

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

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

Push the limits

Odner holds a doctorate in the lab of Harry Asada, Ford Professor of Engineering in the Department of Mechanical Engineering at MIT. Odner says he encouraged students to familiarize themselves with robotics research. Colleagues also frequently shared their work at seminars, giving Odner a holistic view of the field.

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

In 2009, Odhner was a member of the winning team of the DARPA Autonomous Robotic and Manipulation Challenge. Many competing teams were associated with MIT, and the entire program was ultimately led by former MIT associate 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 acquired by Amazon). logistics.

Today, a significant number of RightHand Robotics employees and leaders come from MIT. MIT researchers also explained many early customers purchasing components invented by Odner’s team during the DARPA program.

“In general, we’re so close to MIT that it’s hard to avoid going 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 machine vision and smart grippers to make peace picking robots more adaptable. This combination also limits the amount of training required to operate the robot, and each machine is equipped with the equivalent of a company’s hand-eye coordination.

“The technical part of what we do is that we have to look at unstructured presentations of consumer goods and make a meaningful understanding of what is there,” says Odner.

RightHand Robotics also uses a tool at the end of the arm that combines suction with a new underutilized finger. This gives Odhner more flexibility than robots which rely solely on suction cups and simple grippers.

“In practice, this can help give the hand a passive degree of freedom, a passive movement that it can and cannot actively control,” Odhner said of the robot. “Often they simplify control tasks. They eliminate the problems of being over-constrained and make them more manageable when performing motion planning algorithms.

Data collected by robots is also used to improve reliability over time and inform customer warehousing operations.

“We give people an overview of their inventory, information on how they store their inventory and how they operate both upstream and downstream of the picking that we do. It can give you insight into what you are building, ”says Odhner. “We have a really good idea of ​​what could be causing future problems and we can pass it on to our customers. “

Odhner says warehouse processing could become a much bigger industry if throughput was improved.

“As consumers increasingly enjoy their online shopping options, more and more items need to be added to their ‘virtual’ shopping carts. The availability of people near fulfillment centers tends to be a limiting factor in the growth of e-commerce. All of this shows significant inefficiency in the economy, which is what we are basically trying to remedy, ”says Odner. “We do the less attractive jobs in the warehouse. For example, like sorter guidance, we just pick something, scan it, and place it on the mat all day. We automate these tasks for our clients. Can take your people and you can bring them to what will be felt more directly by the customer. “

Odhner also said more automated distribution centers are helping protect workers’ health and safety, including ergonomic stations where goods are brought to workers for special tasks and increased social distancing. It indicates that it will provide improved metrics. Instead of reducing the number of people working in the warehouse, he says, “At the end of the day, I want a system that plays a role such as controlling quality and overseeing robots. “

Easy robots

This year, the company announces a third version of its picking robot. It features standardized integration and security features to make it easier for warehouse operators to deploy peace picking robots.

“We don’t necessarily understand the extent of our progress in bringing this stand-alone system to market in terms of ease of integration, configuration, security and reliability, but we have robotic systems around the world. It’s huge because it means you can drop shipping, and you can launch and run it with minimal customization, ”says Odhner. “There is no reason for this to be in a box or a pallet and no one can install it. This is our grand vision.

Combination of unique gripper designs with AI and machine vision Source link Combination of unique gripper designs with AI and machine vision



Source link

Comments are closed.