Penn Engineers have developed a system that lets robots see around corners using radio waves processed by AI, a capability that could improve the safety and performance of driverless cars as well as robots operating in cluttered indoor settings like warehouses and factories.
The system, called HoloRadar , enables robots to reconstruct three-dimensional scenes outside their direct line of sight, such as pedestrians rounding a corner. Unlike previous approaches to non-line-of-sight (NLOS) perception that rely on visible light, HoloRadar works reliably in darkness and under variable lighting conditions.
"Robots and autonomous vehicles need to see beyond what's directly in front of them," says Mingmin Zhao , Assistant Professor in Computer and Information Science (CIS) and senior author of a paper describing HoloRadar , presented at the 39th annual Conference on Neural Information Processing Systems (NeurIPS). "This capability is essential to help robots and autonomous vehicles make safer decisions in real time."
Turning Walls Into Mirrors
At the heart of HoloRadar is a counterintuitive insight into radio waves. Compared to visible light, radio signals have much longer wavelengths, a property traditionally seen as a disadvantage for imaging because it limits resolution. Zhao's team realized that, for peering around corners, those longer wavelengths are actually an advantage.
"Because radio waves are so much larger than the tiny surface variations in walls," says Haowen Lai , a doctoral student in CIS and co-author of the new paper, "those surfaces effectively become mirrors that reflect radio signals in predictable ways."
In practical terms, this means that flat surfaces like walls, floors and ceilings can bounce radio signals around corners, carrying information about hidden spaces back to a robot. HoloRadar captures these reflections and reconstructs what lies beyond direct view.
"It's similar to how human drivers sometimes rely on mirrors stationed at blind intersections," says Lai. "Because HoloRadar uses radio waves, the environment itself becomes full of mirrors, without actually having to change the environment."
Designed for In-the-Wild Operations
In recent years, other researchers have demonstrated systems with similar capabilities , typically by using visible light. Those systems analyze shadows or indirect reflections, making them highly dependent on lighting conditions. Other attempts to use radio signals have relied on slow and bulky scanning equipment, limiting real-world applications.
"HoloRadar is designed to work in the kinds of environments robots actually operate in," says Zhao. "This system is mobile, runs in real time and doesn't depend on controlled lighting."
HoloRadar augments the safety of autonomous robots by complementing existing sensors rather than replacing them. While autonomous vehicles already use LiDAR, a sensing system that uses lasers to detect objects in the vehicles' direct line of sight, HoloRadar adds an additional layer of perception by revealing what those sensors cannot see, giving machines more time to react to potential hazards.
Processing Radio With AI
A single radio pulse can bounce multiple times before returning to the sensor, creating a tangled set of reflections that are difficult to untangle using traditional signal-processing methods alone.
To solve this problem, the team developed a custom AI system that combines machine learning with physics-based modeling. In the first stage, the system enhances the resolution of raw radio signals and identifies multiple "returns" corresponding to different reflection paths. In the second stage, the system uses a physics-guided model to trace those reflections backward, undoing the mirror-like effects of the environment and reconstructing the actual 3D scene.
"In some sense, the challenge is similar to walking into a room full of mirrors," says Zitong Lan , a doctoral student in Electrical and Systems Engineering (ESE) and co-author of the paper. "You see many copies of the same object reflected in different places, and the hard part is figuring out where things really are. Our system learns how to reverse that process in a physics-grounded way."
By explicitly modeling how radio waves bounce off surfaces, the AI can distinguish between direct and indirect reflections and determine the correct physical locations of a variety of objects, including people.
From the Lab to the Real World
The researchers tested HoloRadar on a mobile robot in real indoor environments, including hallways and building corners. In these settings, the system successfully reconstructed walls, corridors and hidden human subjects located outside the robot's line of sight.
Future work will explore outdoor scenarios, such as intersections and urban streets, where longer distances and more dynamic conditions introduce additional challenges.
"This is an important step toward giving robots a more complete understanding of their surroundings," says Zhao. "Our long-term goal is to enable machines to operate safely and intelligently in the dynamic and complex environments humans navigate every day."
This research was conducted in the Wireless, Audio, Vision and Electronics for Sensing (WAVES) Lab at the University of Pennsylvania School of Engineering and Applied Science, and was supported by the University of Pennsylvania.
