Spring 2026 GRASP on Robotics: Mingmin Zhao, University of Pennsylvania, “Augmenting Human and Machine Perception with Invisible Signals”

This event was in-person ONLY in Wu and Chen Auditorium…

ABSTRACT

Perception is central to both intelligent machines and human experience, with vision playing a dominant role in how we sense and interpret the world. In this talk, I will explore how invisible wave signals, including radio frequency (RF) and sound, can complement vision by providing access to aspects of the physical world that are difficult to capture through visual sensing alone. I will first present our work on RF-based machine perception, where we leverage signal interactions with the environment to recover information beyond what is directly visible. This enables sensing through occlusion and adverse conditions, inferring structure around corners, and capturing material properties from a distance. I will then turn to acoustic signals and their role in shaping human experience. By modeling how sound propagates in space, we can capture and synthesize immersive audio-visual environments, enabling spatially aware interaction and realistic rendering of complex scenes. I will conclude with a discussion on future directions in integrating RF, acoustics, vision, and language modalities to build more robust representations of the physical world.