UC Berkeley engineers have created new software that combines neural networks with motion planning software to give robots the speed and skill to assist in warehouse environments. (UC Berkeley video courtesy Ken Goldberg lab)
In the past year, lockdowns and other COVID-19 safety measures have made online shopping more popular than ever, but the skyrocketing demand is leaving many retailers struggling to fulfill orders while ensuring the safety of their warehouse employees.
Researchers at the University of California, Berkeley, have created new artificial intelligence software that gives robots the speed and skill to grasp and smoothly move objects, making it feasible for them to soon assist humans in warehouse environments. The technology is described in a paper published online today (Wednesday, Nov. 18) in the journal Science Robotics.
Automating warehouse tasks can be challenging because many actions that come naturally to humans — like deciding where and how to pick up different types of objects and then coordinating the shoulder, arm and wrist movements needed to move each object from one location to another — are actually quite difficult for robots. Robotic motion also tends to be jerky, which can increase the risk of damaging both the products and the robots.
“Warehouses are still operated primarily by humans, because it’s still very hard for robots to reliably grasp many different objects,” said Ken Goldberg, William S. Floyd Jr. Distinguished Chair in Engineering at UC Berkeley and senior author of the study. “In an automobile assembly line, the same motion is repeated over and over again, so that it can be automated. But in a warehouse, every order is different.”
In earlier work, Goldberg and UC Berkeley postdoctoral researcher Jeffrey Ichnowski created a Grasp-Optimized Motion Planner that could compute both how a robot should pick up an object and how it should move to transfer the object from one location to another.
However, the motions generated by this planner were jerky. While the parameters of the software could be tweaked to generate smoother motions, these calculations took an average of about half a minute to compute.
In the new study, Goldberg and Ichnowski, in collaboration with UC Berkeley graduate student Yahav Avigal and undergraduate student Vishal Satish, dramatically sped up the computing time of the motion planner by integrating a deep learning neural network.
Neural networks allow a robot to learn from examples. Later, the robot can often generalize to similar objects and motions.
However, these approximations aren’t always accurate enough. Goldberg and Ichnowski found that the approximation generated by the neural network could then be optimized using the motion planner.
“The neural network takes only a few milliseconds to compute an approximate motion. It’s very fast, but it’s inaccurate,” Ichnowski said. “However, if we then feed that approximation into the motion planner, the motion planner only needs a few iterations to compute the final motion.”
By combining the neural network with the motion planner, the team cut average computation time from 29 seconds to 80 milliseconds, or less than one-tenth of a second.
Goldberg predicts that, with this and other advances in robotic technology, robots could be assisting in warehouse environments in the next few years.
“Shopping for groceries, pharmaceuticals, clothing and many other things has changed as a result of COVID-19, and people are probably going to continue shopping this way even after the pandemic is over,” Goldberg said. “This is an exciting new opportunity for robots to support human workers.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Artificial intelligence software
- Chicago legal-software firm acquired as part of $200 million dealon January 26, 2021 at 8:11 am
Chicago-based Reveal has been acquired as part of a legal-software rollup by a private-equity firm. Reveal is being merged with Brainspace, an artificial-intelligence software company based in Dallas.
- Engineering and artificial intelligence combine to safeguard COVID-19 patientson January 26, 2021 at 7:31 am
Princeton engineers applied artificial intelligence to the task of monitoring and adjusting ventilators for COVID-19 patients, with the goal of easing the burden on medical workers and allowing ...
- Reveal And Brainspace Merge to Become Leading Artificial Intelligence Powered eDiscovery Platformon January 26, 2021 at 7:30 am
Press Release Reveal, a global provider of the leading AI-powered eDiscovery platform, and Brainspace, a global provider of visual analytics for eDiscovery and investigations, announced today that ...
- China is Winning the Artificial Intelligence Race | Opinionon January 26, 2021 at 3:00 am
Although the Biden campaign promised more spending to promote American technological leadership, the scale of the requirement is far greater than either American political party has grasped.
- Artificial Intelligence (AI) Delivers for CloudCommerceon January 26, 2021 at 12:24 am
Our clients are reaping the benefit of our real-world application of artificial intelligence. Our goal is to continue to work toward potentially reducing the costs of advertising by as much as 50%.” ...
Go deeper with Google Headlines on:
Artificial intelligence software
Go deeper with Bing News on:
Advances in robotic technology
- Lasers bring technology to artisan watch crystal engravingon January 26, 2021 at 2:43 am
Historically the preparation of a watch crystal has involved traditional artisan engraving and cutting tools, but a project at Swiss research center EPFL has now applied lasers to the task. In a ...
- Worldwide Industrial Robot Vision Systems Industry to 2025 - Key Drivers, Challenges and Trends - ResearchAndMarkets.comon January 25, 2021 at 8:38 am
The “Global Industrial Robot Vision Systems Market 2021-2025” report has been added to ResearchAndMarkets.com’s offering. The publisher has been monitoring the industrial robot vision systems market ...
- Robots got their name 100 years ago todayon January 25, 2021 at 8:04 am
Exactly one hundred years ago, a play premiered that introduced a significant new word to the world – robot. When the first production of Karel Čapek's R.U.R. opened on January 25, 1921, at the ...
- 100 Years Later, The Future Of Robots Still Lies In Science Fictionon January 25, 2021 at 4:00 am
Every year there is some version of this remembrance on the internet, dated January 25th and full of science fiction references and doom-saying. This is the 2021 version. Today marks the 100th ...
- Scientists create advanced soft robots with liquid crystal elastomerson January 25, 2021 at 3:20 am
The pink strip lies flat on a black-and-white checkerboard surface. It’s rubbery—gummy, almost—and just thicker than an unrolled fruit leather snack. At a glance, the strip seems unremarkable.