Researchers at Stony Brook University have introduced a new navigation system that enables robots to detect objects around corners using commercially available, lightweight sensors. The team presented their findings at ICRA 2025, highlighting potential applications for improved safety in autonomous robots, self-driving vehicles, and delivery systems operating in complex environments.
The research utilizes single-photon LiDAR technology, which can sense faint light signals reflected off surfaces and around obstacles. This approach is inspired by convex mirrors used at blind intersections to help drivers see oncoming traffic. Akshat Dave, assistant professor of Computer Science at Stony Brook and former Postdoctoral Associate at MIT Media Lab, explained the concept: “We asked ourselves, what if a robot could use walls the same way — by turning walls into mirrors?”
Dave noted that the technology has potential uses beyond navigation. “We want to take this project beyond navigation, to challenges that pose real Non-Line-of-Sight problems, like teaching robots to lift hidden objects, exploring and mapping unreachable areas, and conducting search and rescue operations,” he said. “These systems will be able to see the world in ways we do not.”
The project is titled Enhancing Autonomous Navigation by Imaging Hidden Objects using Single-Photon LiDAR and is funded by the National Science Foundation (CMMI-2153855) as well as the NSF Graduate Research Fellowship.
More information can be found in an article by Ankita Nagpal on the AI Innovation Institute website.
