About

Yusuf Guenena

I build the reliability layer for learned robot policies: the runtime monitoring, failure detection, and safe-fallback logic that decides whether a trained policy can be trusted right now, and the sim-to-real plumbing that gets it onto real edge hardware.

I started in electrical engineering. That is where I learned that a system is only as good as its behavior when a component degrades, and that the interesting question is almost never whether something works on the bench.

That instinct moved with me into robotics and intelligent control, and now into an M.S. in Robotics at Wayne State. The hard problem in robotics has shifted from “can the policy do it” to “does it fail loudly when it cannot,” and that gap is where I work: instrumenting a shipped model until it admits it has gone blind, replaying real failures in simulation, and being precise on the page about what runs on the robot versus what is still in sim.

Most of my work runs on a Unitree GO2 with a Jetson Orin NX on its back, which remains the fastest way I know to find out which simulation results were real. My thesis applies the same instinct to quadruped guidance for blind and low-vision users, where following the wrong person is worse than not following at all.

The long-term ambition is straightforward: autonomous machines that stay dependable outside the conditions they were trained for. I am based between Detroit and Houston, and open to robotics-software, Isaac and simulation-reliability, and research-engineering roles, as well as PhD conversations.

Stack: what I actually use

Contact: open to roles & collabs