An imaging and 3-D mapping robot is being developed to help firefighters quickly understand what’s happening inside a structure when it’s ablaze.
The small Segway-like droid being built by University of California, San Diego, engineers can overcome obstacles as it moves through a burning building. It records its surroundings with one thermal and two stereo cameras, which onboard image-processing software then turns into a 3-D map that can be beamed to first responders.
The research group, which includes universities, businesses and the local fire department, hopes that teams of the little robots will one day wheel around commercial and residential fires to quickly identify injured people, hot spots, volatile gases and areas of structural weakness.
By hallucinating the existence of humans, robots can learn how to better cater to people and understand our world, researchers say.
For robots that interact with and react to the world around them as best as possible, scientists want to design machines that know what’s in their surroundings. Attempts to identify an item based on its appearance can run into a gauntlet of problems — for example, an object might differ in how it looks over time depending on the lighting or the angle the robot views it from, and one item might differ enough from a similar one when it comes to color, size or shape to confound a droid’s limited knowledge.
One way researchers want to improve a robot’s ability to identify objects is to help it recognize the context an item lies within. For instance, if a machine recognizes a setting as a kitchen, that could help it figure out that objects on a countertop might be cups, bowls or utensils.
The builders of UC Berkeley’s cockroach-inspired STAR robot have strapped a camera onto the little machine to see the world from its angle.
Engineers at the university’s Biomimetic Millisystems Lab have designed the little transformer robot to “adapt its stiffness, height, and leg-to-surface contact angle.” At full speed, it can run at 5.2 meters or 43 body lengths per second. They say it’s the world’s fastest untethered crawling bot.
The buzzing sound coming from one Harvard lab isn’t a fly infestation but rather a tiny, insect-like robot. The approximately penny-sized robot dubbed RoboBee mimics the aerial prowess of houseflies, one of the most agile fliers on Earth. And like a fly, RoboBee features two independently flapping wings that allow it to hover or perform basic controlled flight maneuvers.
“This is the world’s first demonstration of a fully unconstrained flapping wing insect-scale robot,” says Kevin Ma, a doctoral student at the Harvard University Microrobotics Laboratory and lead author of a paper published this week in Science describing the machine. While small helicopters and hummingbird-size flapping robots exist, Ma says, those creations are around ten times the size of the RoboBee.
“We’re very impressed by the maneuverability and agility that [insects] like bees and flies share,” he continues. “One day, a robot like this could afford us that same agility and maneuverability.”