Breakthrough CSAIL system suggests robots could one day be able to see well enough to be useful in people’s homes and offices.
Humans have long been masters of dexterity, a skill that can largely be credited to the help of our eyes. Robots, meanwhile, are still catching up.
Certainly there’s been some progress: For decades, robots in controlled environments like assembly lines have been able to pick up the same object over and over again. More recently, breakthroughs in computer vision have enabled robots to make basic distinctions between objects. Even then, though, the systems don’t truly understand objects’ shapes, so there’s little the robots can do after a quick pick-up.
In a new paper, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), say that they’ve made a key development in this area of work: a system that lets robots inspect random objects, and visually understand them enough to accomplish specific tasks without ever having seen them before.
The system, called Dense Object Nets (DON), looks at objects as collections of points that serve as sort of visual roadmaps. This approach lets robots better understand and manipulate items, and, most importantly, allows them to even pick up a specific object among a clutter of similar — a valuable skill for the kinds of machines that companies like Amazon and Walmart use in their warehouses.
For example, someone might use DON to get a robot to grab onto a specific spot on an object, say, the tongue of a shoe. From that, it can look at a shoe it has never seen before, and successfully grab its tongue.
“Many approaches to manipulation can’t identify specific parts of an object across the many orientations that object may encounter,” says PhD student Lucas Manuelli, who wrote a new paper about the system with lead author and fellow PhD student Pete Florence, alongside MIT Professor Russ Tedrake. “For example, existing algorithms would be unable to grasp a mug by its handle, especially if the mug could be in multiple orientations, like upright, or on its side.”
The team views potential applications not just in manufacturing settings, but also in homes. Imagine giving the system an image of a tidy house, and letting it clean while you’re at work, or using an image of dishes so that the system puts your plates away while you’re on vacation.
What’s also noteworthy is that none of the data was actually labeled by humans. Instead, the system is what the team calls “self-supervised,” not requiring any human annotations.
Two common approaches to robot grasping involve either task-specific learning, or creating a general grasping algorithm. These techniques both have obstacles: Task-specific methods are difficult to generalize to other tasks, and general grasping doesn’t get specific enough to deal with the nuances of particular tasks, like putting objects in specific spots.
The DON system, however, essentially creates a series of coordinates on a given object, which serve as a kind of visual roadmap, to give the robot a better understanding of what it needs to grasp, and where.
The team trained the system to look at objects as a series of points that make up a larger coordinate system. It can then map different points together to visualize an object’s 3-D shape, similar to how panoramic photos are stitched together from multiple photos. After training, if a person specifies a point on a object, the robot can take a photo of that object, and identify and match points to be able to then pick up the object at that specified point.
This is different from systems like UC-Berkeley’s DexNet, which can grasp many different items, but can’t satisfy a specific request. Imagine a child at 18 months old, who doesn’t understand which toy you want it to play with but can still grab lots of items, versus a four-year old who can respond to “go grab your truck by the red end of it.”
In one set of tests done on a soft caterpillar toy, a Kuka robotic arm powered by DON could grasp the toy’s right ear from a range of different configurations. This showed that, among other things, the system has the ability to distinguish left from right on symmetrical objects.
When testing on a bin of different baseball hats, DON could pick out a specific target hat despite all of the hats having very similar designs — and having never seen pictures of the hats in training data before.
“In factories robots often need complex part feeders to work reliably,” says Florence. “But a system like this that can understand objects’ orientations could just take a picture and be able to grasp and adjust the object accordingly.”
In the future, the team hopes to improve the system to a place where it can perform specific tasks with a deeper understanding of the corresponding objects, like learning how to grasp an object and move it with the ultimate goal of say, cleaning a desk.
Learn more: Robots can now pick up any object after inspecting it
The Latest on: Computer vision
[google_news title=”” keyword=”computer vision” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Computer vision
- Computer Vision SAAS Startup Assert AI Secures USD 4 Mn in Series A Roundon April 29, 2024 at 10:26 pm
The Mumbai-based platform plans to deploy the raised funds to bolster its presence in essential markets, enhance research and development efforts, and continue pioneering new advancements in computer ...
- Embedded Vision Summit® Announces Full Conference Program for Edge AI and Computer Vision Innovators, May 21-23 in Santa Clara, Californiaon April 29, 2024 at 1:12 pm
The Edge AI and Vision Alliance, a worldwide industry partnership, today announced the full program for the 2024 Embedded Vision Summit, taking place May 21-23 at the Santa Clara Convention Center, ...
- Dalmia Transport Selects Roadzen's DrivebuddyAI to Enhance Fleet Safety with Advanced Computer Visionon April 29, 2024 at 7:01 am
DrivebuddyAI, a subsidiary of Roadzen, is at the forefront of leveraging AI for enhanced fleet safety and insurance, offering innovative solutions like ADAMATICS that integrate ADAS with telematics.
- University of Central Florida: Computer Vision Researcher Creates Privacy Software for Surveillance Videoson April 28, 2024 at 11:50 pm
Computer vision can be a valuable tool for anyone tasked with analyzing hours of footage because it can speed up the process of identifying individuals. For example, law enforcement may use it to ...
- The Role of Computer Vision in Cybersecurityon April 27, 2024 at 2:12 am
As the cybersecurity arena is often changing from day to day, organizations are constantly searching for new methods that will better their odds of successfully keeping cybersecurity out of their ...
- How Computer Vision Is Transforming Cybersecurityon April 27, 2024 at 1:40 am
Explore how computer vision revolutionizes cybersecurity, enhancing threat detection and surveillance systems through innovative technology.
- Computer Vision Market Ethnography Techniques for Deeper Consumer Understanding A Strategic Approachon April 25, 2024 at 3:22 pm
Computer Vision Market is valued approximately at USD 11 billion in 2019 and is anticipated to grow with a healthy growth rate of more than 7.8% over the forecast period 2020-2027. A computer vision ...
- Computer vision researcher develops privacy software for surveillance videoson April 24, 2024 at 5:00 pm
Computer vision can be a valuable tool for anyone tasked with analyzing hours of footage because it can speed up the process of identifying individuals. For example, law enforcement may use it to ...
- How e-Commerce Can Leverage Computer Vision Technology To Boost Sector – NCCon April 22, 2024 at 11:45 pm
Exploratory Study on the Application of Computer Vision Technology for E-Commerce Sector Growth In Nigeria,” published by the ...
via Bing News