Which way to the fridge? Common sense helps robots navigate

July 20, 2020

PITTSBURGH--A robot travelling from point A to point B is more efficient if it understands that point A is the living room couch and point B is a refrigerator, even if it's in an unfamiliar place. That's the common sense idea behind a "semantic" navigation system developed by Carnegie Mellon University and Facebook AI Research (FAIR).

That navigation system, called SemExp, last month won the Habitat ObjectNav Challenge during the virtual Computer Vision and Pattern Recognition conference, edging a team from Samsung Research China. It was the second consecutive first-place finish for the CMU team in the annual challenge.

SemExp, or Goal-Oriented Semantic Exploration, uses machine learning to train a robot to recognize objects -- knowing the difference between a kitchen table and an end table, for instance -- and to understand where in a home such objects are likely to be found. This enables the system to think strategically about how to search for something, said Devendra S. Chaplot, a Ph.D. student in CMU's Machine Learning Department.

"Common sense says that if you're looking for a refrigerator, you'd better go to the kitchen," Chaplot said. Classical robotic navigation systems, by contrast, explore a space by building a map showing obstacles. The robot eventually gets to where it needs to go, but the route can be circuitous.

Previous attempts to use machine learning to train semantic navigation systems have been hampered because they tend to memorize objects and their locations in specific environments. Not only are these environments complex, but the system often has difficulty generalizing what it has learned to different environments.

Chaplot -- working with FAIR's Dhiraj Gandhi, along with Abhinav Gupta, associate professor in the Robotics Institute, and Ruslan Salakhutdinov, professor in the Machine Learning Department -- sidestepped that problem by making SemExp a modular system.

The system uses its semantic insights to determine the best places to look for a specific object, Chaplot said. "Once you decide where to go, you can just use classical planning to get you there."

This modular approach turns out to be efficient in several ways. The learning process can concentrate on relationships between objects and room layouts, rather than also learning route planning. The semantic reasoning determines the most efficient search strategy. Finally, classical navigation planning gets the robot where it needs to go as quickly as possible.

Semantic navigation ultimately will make it easier for people to interact with robots, enabling them to simply tell the robot to fetch an item in a particular place, or give it directions such as "go to the second door on the left."

Carnegie Mellon University

Related Robot Articles from Brightsurf:

Autonomous robot plays with NanoLEGO
Atoms and molecules behave in a completely different way to macroscopic objects and each brick requires its own ''instruction manual''.

Robot technology for everyone or only for the average person?
Robot technology is being used more and more in health rehabilitation and in working life.

Soft robot, unplugged
It's balloon art on steroids: a pneumatic, shape-changing soft robot capable of navigating its environment without requiring a tether to a stationary power source.

Trash talk hurts, even when it comes from a robot
Trash talking has a long and colorful history of flustering game opponents, and now researchers at Carnegie Mellon University have demonstrated that discouraging words can be perturbing even when uttered by a robot.

A robot with a firm yet gentle grasp
Human hands are skilled at manipulating a range of objects.

You can't squash this roach-inspired robot
A new insect-sized robot created by researchers at the University of California, Berkeley, can scurry across the floor at nearly the speed of a darting cockroach -- and it's nearly as hardy as a cockroach, too: Try to squash this robot under your foot, and more than likely, it will just keep going.

In the shoes of a robot: The future approaches
Identifying with someone is an exercise that makes us understand them deeply, empathize with them, and helps us overcome mistrust and prejudice.

Now your phone can become a robot that does the boring work
Purdue University researchers have developed a smartphone app that allows a user to easily program any robot to perform a task, dramatically bringing down the costs of building and programming mobile robots.

Better together: human and robot co-workers
More and more processes are being automated and digitised. Self-driving delivery vehicles, such as forklifts, are finding their way into many areas -- and companies are reporting potential time and cost savings.

Robot therapists need rules
Interactions with artificial intelligence (AI) will become an increasingly common aspect of our lives.

Read More: Robot News and Robot Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.