Prof Mingmin Zhao (right) has been working on a radio vision system for robots. If you want to find out whether your robot can see through smoke, you'll need some smoke.
However, a University of Pennsylvania student experienced a surprise while setting up a late-night experiment to test such a robot. Shortly after activating the smoke machine, a loud fire alarm went off. "The whole building got triggered," says Mingmin Zhao, smiling. "My student called me. He was very surprised."
This incident was a minor setback for the team developing a robot equipped with an innovative radio-based sensing system. Radio waves could enable robots or autonomous vehicles to see through thick smoke, intense rain, or even around corners. These waves can even detect concealed weapons.
Simulating visual imagery based on radio waves is an unusual approach for robots and autonomous vehicles, as more established methods in these fields include regular optical cameras, light detection and ranging (Lidar), and other sensors. Nonetheless, Prof Zhao and his students have developed a potentially powerful way for robots to see using radio waves.
Radar, which uses radio waves, has been utilized for decades to track aircraft, ships, and weather patterns. However, the spinning array on Prof Zhao's robot emits radio waves in all directions. An on-board artificial intelligence (AI) system then constructs a 3D view of the environment using this information.
Prof Zhao explains, "What we have been trying to do here is basically help robots obtain superhuman vision – to see in scenarios where human eyes or traditional visual sensors cannot." He suggests that this technology could assist future search-and-rescue robots in saving people from burning buildings.
In subsequent tests, the team used a clear plastic box filled with smoke around the robot's spinning equipment to avoid triggering any nearby alarms. By combining radio waves with AI, the robot can create a 3D picture of its environment. Although humans cannot see radio waves, they are a form of light, part of the electromagnetic spectrum that includes X-rays and gamma rays. Only a small portion of this spectrum is classified as visible light.
As a type of light, radio waves can reflect off surfaces and materials, albeit differently from visible light. Prof Zhao and his colleagues have designed their robot to sense these radio wave reflections. A crucial advantage is that radio waves are much longer than visible light waves, allowing them to pass through tiny smoke particles without obstruction.
Additionally, Prof Zhao has been working on adapting the technology so that the robot can see partially around corners. He likens this capability to a hall of mirrors, but for radio waves instead of visible light.
Post a Comment