Zaleski Discovery Award Backs Wearable Safety Technology for Blind Travelers

Most wearable vision systems for blind travelers try to interpret everything in view. That costs power, memory, and time. Marius Schneider wants a device that reacts to danger before it knows what the danger is. A new College of Engineering award will fund the attempt.

Schneider, a postdoctoral scholar in the Bionic Vision Lab of Michael Beyeler, an Associate Professor of Computer Science at UC Santa Barbara, has received the 2026-27 James V. & Beverly R. Zaleski Discovery Award in Robotics and Computing from The Robert Mehrabian College of Engineering. The award provides up to $94,000 for his project, “Residual Event Affordances: Neuromorphic Safety Computation for Mobile Edge Systems.”

At its center is an event camera, which reports changes in brightness pixel by pixel the instant they occur rather than capturing full frames. Less wasted data means faster warnings and longer battery life, but there is a catch: the wearer's own walking and turning floods the sensor with motion. Schneider's system would learn to predict the visual changes caused by routine movement and subtract them. What remains is the approaching cyclist or the sudden curb. The device would estimate collision risk and direction, then tell the user to stop, slow down, or step aside, without needing to decide whether the threat was a bicycle, a trash can, or a jogger.

“Biological vision responds to immediate danger before fully interpreting everything in view,” Schneider said. “If a car swerves toward you while you're crossing the street, you jump out of the way before you've consciously identified what kind of car it is.”

The approach grew out of Mouse-vs-AI, a benchmark platform Schneider and colleagues presented at the conference on Neural Information Processing Systems (NeurIPS), which places mice and AI agents in comparable virtual foraging tasks. When lighting, fog, or clutter changed, the AI agents typically needed retraining. The mice adapted on the first encounter, and on the energy of a few calories.

Schneider will begin in a simulated urban environment, where a virtual blind pedestrian wearing an event camera encounters curbs, moving people, and changing weather. He will measure his model against conventional camera-based AI and existing event-camera systems on warning time, missed hazards, false alarms, and energy use, then test whether it can run on neuromorphic hardware, brain-inspired chips that mimic biological neurons. Both the model and the benchmark will be released as open-source resources. Within five years, he hopes to put a wearable prototype in the hands of blind and low-vision users.

“Marius is exactly the kind of researcher this award is meant to catalyze, original, technically deep, generous as a mentor, and ready to define an independent direction,” Beyeler said.

“The deeper hope is that this kind of technology could shift what an ordinary day looks like for someone with a visual impairment,” Schneider said, “that it becomes possible to explore a new city, or take an unplanned detour, or move through a crowd, with the same degree of casual confidence that sighted people take for granted.”

Adapted from a story originally written by Andrew Masuda for The Robert Mehrabian College of Engineering.