Hamza Basharat
All work

Autonomous UAV disaster response

SkyResQ

Status
Research / prototype
Role
AI & UAV Engineer (Intern)
Organisation
NESCOM, National Development Complex
Year
2025

The problem

In a disaster zone, finding people fast is the whole problem, and a human pilot watching a UAV feed cannot search a wide area quickly or reliably.

Outcome

Evaluated by
NESCOM / NDCEvaluated byPakistan national defence research organisation.
Validation
Gazebo + flightValidationSimulation-first, then integration testing.
Audience
Government stakeholdersAudience
Gazebo simulation of the UAV airframe, used to validate the perception stack before flight.

Gazebo simulation of the UAV airframe, used to validate the perception stack before flight.

Gazebo simulation of the UAV airframe used to validate the perception stack before flight, and the physical hexacopter airframe.

Approach

  • 01

    Built detection and tracking pipelines in Python/OpenCV for aerial perception under the conditions a search UAV actually flies in.

  • 02

    Validated the stack in Gazebo simulation before flight, with integration testing across the perception and control layers.

  • 03

    Presented results directly to Pakistani government stakeholders evaluating the system for national emergency preparedness.

Stack

  • Python
  • OpenCV
  • Gazebo
  • PX4 SITL
  • MAVSDK
  • ROS2

Restricted. Defence-adjacent work. Keep the public description at the level the CV already states and no further.