ROBOTICS & AI RESEARCH ENGINEER

Teaching robots to say what they mean, clearly enough to trust.

I research and build the systems that let humanoid robots communicate their intentions to people, from sim-to-real pipelines on real hardware to deployed embedded AI. MSc AI & Robotics (Commendation), University of Hertfordshire.

95%
Intent clarity in verbal HRI condition, RoSAS-validated
d = 0.58
Effect size, verbal vs. gestural communication
2
Humanoid platforms engineered, iCub & JD
ABOUT

Engineer first. Researcher by conviction.

I work at the boundary between robotics research and shipped engineering. My academic work asks how humanoid robots should communicate so that people trust them appropriately, not too little, not too much. My applied work has been building the embedded systems and edge AI pipelines that make robots, and the products around them, actually work in the field.

That combination shapes how I think about every project: a result only matters once it survives contact with real hardware, real users, and conditions nobody designed for in the lab. I bring the same standard to a fresh dataset on a humanoid platform as I do to firmware shipping in a safety-critical product.

I'm currently pursuing PhD research in human-robot interaction and AI reliability, while remaining open to robotics and AI engineering roles where that same standard of rigor is valued.

Portrait of Munawar Kazmi
MSc AI & Robotics
Commendation · University of Hertfordshire · 2023–2024
BEng Mechatronics Engineering
NUST · 2018–2022
FOR ACADEMIC CONTACTS
Actively applying to PhD programmes in HRI, AI reliability, and trust calibration. Happy to share research proposals on request.
FOR HIRING TEAMS
Open to robotics and AI engineering roles in the UK, EU, and USA. UK Graduate Visa valid through September 2026.
FEATURED RESEARCH

Sim-to-real HRI on iCub & JD humanoid platforms

MSc thesis research, University of Hertfordshire, on how humanoid robots should communicate need-states to build appropriate, calibrated trust.

iCub · JD Humanoid · Isaac Sim · ROS2

Enhancing Human-Robot Companionship: Comparing Verbal and Non-Verbal Communication Cues in Humanoid Robots

MSc Thesis · University of Hertfordshire · Supervised by Prof. Patrick Holthaus
iCub humanoid robot platform in the lab
iCub humanoid · IIT
JD humanoid robot platform used in the formal trust-calibration study
JD humanoid · EZ-Robot

I built a full sim-to-real pipeline across both the iCub and JD humanoid platforms, developing a high-fidelity Isaac Sim digital twin and engineering the hardware integration for both robots. The formal trust-calibration study, comparing verbal and gestural communication strategies for conveying robot need-states, was conducted on the JD platform with 20 participants in a counterbalanced, RoSAS-validated design.

Why JD for the formal study: early platform testing on iCub surfaced a well-documented uncanny valley effect, its hyper-realistic appearance produced participant discomfort that would have confounded trust measurements. The JD platform's more stylised appearance allowed for natural, unguarded participant responses, so the controlled study proceeded on JD while engineering work continued across both platforms.

Verbal communication produced significantly clearer intent conveyance than gestural cues alone, with comparable engagement and warmth across both modalities, evidence that hybrid verbal-gestural strategies are the right design target for companion robots.

d = 0.58
Effect size, clarity: verbal vs. gestural (p = 0.017)
95%
Intent identification accuracy, verbal condition
80%
Intent identification accuracy, gestural condition
N=20
Within-subjects, counterbalanced, RoSAS-validated
TRY IT · VERBAL VS. NON-VERBAL
Robot states its need directly
Intent identification accuracy 95%
SEE IT IN ACTION · JD HUMANOID
Verbal condition · robot states its need directly
Non-verbal condition · robot communicates via gesture (muted, tap to unmute)
"Munawar demonstrated remarkable technical proficiency, creativity, and a strong work ethic… a valuable asset to academic or professional institutions."
Dr Patrick Holthaus · Senior Research Fellow, University of Hertfordshire · MSc Supervisor
EXPERIENCE

From lab to deployed hardware

Visiting Lecturer, AI & Robotics
Aug 2025 – Present
Pak-Turk Maarif Schools · Multan, Pakistan
  • Designed an ML curriculum for 30+ students; teams achieved 92% model accuracy with 28% average error reduction on custom classification tasks.
Embedded Systems Engineer
Jan 2025 – May 2025
Muxtronics (Contract) · Multan, Pakistan
  • Engineered deterministic C++ firmware for real-time image processing on ESP32, reducing peak RAM by 60%.
  • Architected a LoRa mesh protocol achieving under 3 second alert latency across 100m field trials in a safety-critical deployed product.
Robotics Integration Specialist
Jan 2024 – May 2024
Robot House · University of Hertfordshire
  • Architected a gesture recognition and motion planning pipeline in Unity/C++ for the iCub humanoid, reducing user frustration by 40% and improving HRI task efficiency by 25%.
  • Deployed PyTorch-based non-verbal communication models onto iCub's real-time control loop, lifting user engagement from 4.7 to 5.2 on a 1–7 Likert scale.
Research Associate
May 2023 – Dec 2023
University of Hertfordshire
  • Fine-tuned TensorFlow LLMs for real-time robotics inference on the Unitree Go1 quadruped, cutting inference latency by 29% across 200 trials.
  • Integrated optimised models into the control loop, improving platform responsiveness by 35% with 99.5% runtime stability.
Embedded Systems Intern
Mar 2022 – Apr 2022
NCRA, National Centre of Robotics & Automation · Islamabad
  • Optimised bare-metal C firmware for embedded controllers, achieving 40% faster processing and 98% reliability across 100+ safety-critical test cycles.
PROJECTS

Built, deployed, measured

Every project here shipped to real hardware with quantified outcomes, not benchmark numbers alone.

C++20 ROS2 Nav2 TurtleBot3
ROS2 Autonomous Navigation & Deterministic Planning
A high-performance C++20 Global Planner plugin for ROS2 Nav2 using A* and D* Lite, validated on TurtleBot3 with strict protective-stop safety guarantees.
22%
faster replanning
24%
travel time reduction
View on GitHub →
TensorRT Jetson Nano CNN
Edge AI Optimisation on Jetson Nano
TensorRT optimisation of CNN and gesture recognition models, enabling real-time decentralised motor control across a multi-robot system.
40%
latency reduction
96%
accuracy maintained
View on GitHub →
ROS2 LLM Jetson Orin
ROS2 LLM Safety Verifier
A real-time hallucination detector for ROS2 Nav2 that intercepts unsafe trajectory commands before they reach robot hardware, validated on TurtleBot3 with Jetson Orin Nano.
94%
unsafe trajectory catch rate
<50ms
detection latency
View on GitHub →
ESP32 LoRa Mesh Deployed
ESP32-CAM Motion Detector
Deterministic C++ firmware for image processing on ESP32-CAM with a LoRa mesh alert protocol, shipped as a deployed safety-critical product.
93.8%
detection accuracy
60%
RAM reduction
View on GitHub →
TECHNICAL SKILLS

Tools I ship with

ROBOTICS & SOFTWARE
  • C++20
  • Python
  • ROS2 (Nav2, Plugin Dev)
  • Git & CI/CD
  • Docker
SIMULATION & DIGITAL TWINS
  • Isaac Sim
  • MuJoCo
  • Gazebo
  • Unity
  • Sim-to-Real Transfer
AI & PERCEPTION
  • PyTorch
  • TensorFlow
  • TensorRT
  • Computer Vision
  • LLM Integration
HARDWARE & EMBEDDED
  • iCub & JD Humanoid
  • Unitree Go1
  • Jetson Nano
  • ESP32 & LoRa
  • Bare-Metal C/C++
PUBLICATIONS

Research output

Enhancing Human-Robot Companionship: Comparing Verbal and Non-Verbal Communication Cues in Humanoid Robots
Kazmi, S.M.S. (2025)
Submitted to MDPI Robotics · Under Review
Read Paper (PDF) →
Under Review
SPEAKING & TEACHING

In the room

Munawar Kazmi presenting at the University of Hertfordshire
TALK · UNIVERSITY OF HERTFORDSHIRE
AI & Robotics in Education Conference
Presented on HRI and edge AI applications to students and faculty, with live robot demonstrations of the companionship research.
Munawar Kazmi leading a hands-on robotics and ML workshop at Pak-Turk Maarif Schools
WORKSHOP · PAK-TURK MAARIF SCHOOLS
Hands-On Robotics & ML Workshop
Led practical sessions covering gesture control, neural networks, and real-time AI deployment. Teams built and trained working classifiers during the session.
TESTIMONIALS

What they say

Munawar demonstrated remarkable technical proficiency, creativity, and a strong work ethic. He actively sought feedback and incorporated it into his work, demonstrating a commitment to continuous improvement. His innovative approach, coupled with a strong foundation in research and development, positions him as a valuable asset to academic or professional institutions.
Dr Patrick Holthaus
Senior Research Fellow & Visiting Lecturer · University of Hertfordshire · MSc Supervisor
Munawar demonstrated exceptional skill in embedded AI deployment during his contract at Muxtronics, leading the ESP32-CAM prototype to 93.8% accuracy and optimizing real-time processing by 60%, a true asset for any robotics team.
Waheed Shah
CEO · Muxtronics
GET IN TOUCH

Let's build
something real.

Open to PhD research collaboration in HRI and AI reliability, and to robotics and AI engineering roles in the UK, EU, and USA.

ACADEMIC & RESEARCH CONTACTS
Pursuing PhD opportunities in human-robot interaction and AI reliability. Happy to share full research proposals.
Email about research →
HIRING TEAMS
Open to robotics and AI engineering roles. UK Graduate Visa valid through September 2026, sponsorship welcome.
Email about roles →