Menu
MIT tries to make household robots better with object-detection algorithm

MIT tries to make household robots better with object-detection algorithm

The technology could let robots better identify and handle objects

A new algorithm could let robots more precisely identify and handle objects around them, making them more useful at completing household tasks.

The algorithm, developed by Massachusetts Institute of Technology researchers and discussed in a paper released Monday, allows robots to gather multiple perspectives of an object, quickly aggregate those images and then use that information to identify the object, according to the school.

But don't expect the algorithm to help a robot clear plates and glasses from a table just yet, said Lawson Wong, a graduate student in electrical engineering and computer science, and the paper's lead author. "As it is now, it's still very far from commercialization," he said.

Improving object detection is just one step in equipping robots to complete house work.

For robots to perform useful tasks in the home, they have to know more than simply how many cups and plates are on the table, he said. If a robot was being used to prepare a meal, for example, it would also have to know what temperature to cook the food or where to find the recipe's ingredients.

Still, the algorithm could eventually help software better compute changes that occur in a home when people move objects and add or remove items.

"The software we use doesn't allow us to capture objects that move over time," said Wong.

Multiple-perspective algorithms allow a robot to identify up to four times as many objects than is possible using a single perspective, and these algorithms also help reduce mis-identifications, according to the researchers.

"If you run [images] through a standard view detection, you will miss a lot of objects," said Wong.

The algorithm also successfully addressed a downside of the multiple-perspective approach: that it can prove time-consuming because it increases exponentially the number of calculations the robot must make, often preventing the robot from completing tasks quickly enough.

The researchers noted that object detectors frequently fail although object recognition is one of the most researched topics in artificial intelligence.

Fred O'Connor writes about IT careers and health IT for The IDG News Service. Follow Fred on Twitter at @fredjoconnor. Fred's e-mail address is fred_o'connor@idg.com

Subscribe here for up-to-date channel news

Follow Us

Join the New Zealand Reseller News newsletter!

Error: Please check your email address.

Tags roboticsMassachusetts Institute of Technology

Featured

Slideshows

Tight lines as Hooked on Lenovo catches up at Great Barrier Island

Tight lines as Hooked on Lenovo catches up at Great Barrier Island

​Ingram Micro’s Hooked on Lenovo incentive programme recently rewarded 28 of New Zealand's top performing resellers with a full-on fishing trip at Great Barrier Island for the third year​ in a row.

Tight lines as Hooked on Lenovo catches up at Great Barrier Island
Inside the AWS Summit in Sydney

Inside the AWS Summit in Sydney

As the dust settles on the 2017 AWS Summit in Sydney, ARN looks back an action packed two-day event, covering global keynote presentations, 80 breakout sessions on the latest technology solutions, and channel focused tracks involving local cloud stories and insights.

Inside the AWS Summit in Sydney
Channel tees off on the North Shore as Ingram Micro hosts annual Cure Kids Charity golf day

Channel tees off on the North Shore as Ingram Micro hosts annual Cure Kids Charity golf day

Ingram Micro hosted its third annual Cure Kids Charity Golf Tournament at the North Shore Golf Club in Auckland. In total, 131 resellers, vendors and Ingram Micro suppliers enjoyed a round of golf consisting of challenges on each of the 18 sponsored holes, with Team Philips taking out the top honours.

Channel tees off on the North Shore as Ingram Micro hosts annual Cure Kids Charity golf day
Show Comments