Chris Baraniuk
Technological journalist
Sylvia Zhang
Prof Mingmin Zhao (right) worked on a radio vision system for robots
If you want to know if your robot can see through the smoke, well, you will need smoke.
But a student from the University of Pennsylvania had a shock when they started to set up an late evening experience to test such a robot.
Shortly after launching the switch on the manure machine, a strong fire alarm has died out.
“The entire building was triggered,” said Mingmin Zhao of the University of Pennsylvania, smiling. “My student called me. He was very surprised.”
The incident was a minor setback for the team developing a robot equipped with an innovative radio detection system.
Radio waves could allow robots or autonomous vehicles to see through thick smoke, intense rain – or even in corners. Such waves can even detect hidden weapons.
But the simulation of visual images based on radio waves is an unusual approach for robots and autonomous vehicles. Regular optical cameras are much more established in these fields, regular optical cameras, light detection and diffusion (LIDAR) and other sensors.
However, Professor Zhao and his students developed a potentially powerful means for robots to see the use of radio waves.
Of course, radar, which uses radio waves, has been used for decades to follow planes, ships and weather.
But the rotation board on Professor Zhao’s robot launches radio waves in all directions.
An integrated artificial intelligence system (AI) then builds a 3D environment of the environment with this information.
“What we have tried to do here is essentially helping robots to get a superhuman vision – see in scenarios where human eyes or traditional visual sensors cannot,” said Professor Zhao.
He suggests that technology could help a future research and rescue robot save people from a fire building.
Subsequent bot tests used a transparent plastic box full of smoke placed around its rotation equipment, in order to avoid triggering nearby fire alarms.
Sylvia Zhang
Radio waves combined with AI create a 3D image for the robot
Although humans cannot see them, radio waves are a form of light in the sense that they are part of the electromagnetic spectrum, which also includes X -rays and gamma rays. Only a small part The spectrum is classified as visible light.
Being light, radio waves can reflect on surfaces and materials, but in a slightly different way from visible light. Professor Zhao and his colleagues have designed their robot so that he can feel these radio reflections.
The crucial factor here is that radio waves are much longer than visible light waves, which means that they are not blocked by tiny smoke particles.
Professor Zhao says he also worked on the adaptation of technology so that the robot can see part of the way a corner. Think about it like a mirror room, he suggests, just for radio waves rather than visible light.
“It is a really interesting and quite impressive work,” said Friedemann Reinhard at Rostock University in Germany, which was not involved in work. In 2017, Professor Reinhard and his colleagues described how Wi-Fi signals could allow spies to see in private rooms.
A slight limitation is that the rotation table cannot, by definition, see in all directions at the same time. Prof Reinhard says that a lot of data processing carried out by the system seems necessary to clean the image that results from this spinning device.
However, the robot sends radio waves to the strip of millimeter waves (waves between one and ten millimeters long). This is the same technology used for certain 5G installations.
“It is potentially very attractive, it is a very well understood and inexpensive technology,” explains Professor Reinhard. “I would certainly love to see an autonomous car driving only on the radar.”
Wavsens
Fabio Da Silva is working on a radio imaging system
But it is possible to avoid using radio-emitting devices to have a complete image, explains Fabio Da Silva, founder and director general of the American company Wavsens, which also develops radio detection technology.
“We have created an algorithm that allows you to detect all the space instantly and continuously so that we do not have to run our antennas,” he said.
He describes the system as similar to echolocation, used by bats. He sends radio waves and “listens” to the way the waves come back, which reveals the shape of everything they hit.
Some researchers have used radio waves to detect hidden weapons such as handguns and hidden knives.
The radio waves can even “” “fingerprint” the details of a room. Then, if it is scanned again later, it would reveal if objects in the room have been moved.
Last year, German scientists proposed that countries use this method to examine the management of other countries in their nuclear weapons. It would be a way of knowing if someone had moved the warheads, for example.
Getty images
Radio systems could be a useful addition to scanners on autonomous cars
In addition, Luana Olivieri at the University of Loughborough explored using a different form of non -visible electromagnetic radiation, the waves of Térahertz. These are shorter than radio waves but longer than visible light waves. “This wavelength is particularly unexplored,” said Dr. Olivieri.
It is possible to see through objects and analyze the materials using this form of radiation, she adds. Such a system could even, in theory, identify specific drugs by detecting their chemical structure.
But although materials can help a lifting bot find a trapped person in a future disaster, it also has other applications. Police forces and soldiers have access to radio technology that allows them to see through doors and walls, to some extent.
“War fighting is certainly a market to which it is addressed. It can be used to find and kill someone,” said Da Silva. He exhibited Wavsens technology at the US Department of Defense and the Israeli Defense Ministry, he said.
And yet, these applications are not entirely surprising, suggests that Professor Reinhard, who emphasizes that a range of emerging technologies has in principle facilitated the detection and attack of people.
“Maybe the radar seems frightening-but cheap drones and cameras are the much more dangerous thing,” he said.
