
Detect, recover, or halt.
A language model proposes a route. The shield checks it, replaces it when it is wrong, and stops when no safe route exists.
I build the layers that stop an unsafe plan before hardware moves.
Drag a goal. The robot replans.
Drag the start, a goal or the zone.
unsafe routes from language models got past the safety verifier.
0 of 599 safe routes refusedcertified legibility bounds hold when re-checked.
a ceiling, not a best guesssealed goals made the navigation shield halt instead of inventing a route.
0 unsafe recoveries sent onRobotics and AI engineering in C++20, Python and ROS 2, with embedded firmware and PyTorch. Available on immediate notice, with UK, EU and US hours.
MSc AI and Robotics with Commendation, University of Hertfordshire. Research on legible motion, verifying language-model planners, and human-robot interaction.

A language model proposes a route. The shield checks it, replaces it when it is wrong, and stops when no safe route exists.

Certified upper and lower bounds on legibility under a path budget, so a hard world can be told apart from a weak planner.

One planted trap per instruction, answers in a checkable action language, and every label a proof. No human or model does the judging.

I work at the boundary between robotics research and shipped engineering.
“From the initial stages of designing interactive scenarios for the robot to conducting experiments with human participants and analysing results, Munawar demonstrated remarkable technical proficiency, creativity, and a strong work ethic.”Dr Patrick Holthaus Reader in Interactive Assistive Technology, University of Hertfordshire. MSc supervisor.
hello@munawarkazmi.com