All problems
Robotics
Real-time SLAM for Indoor Drone Navigation
Code: ANX-RP-003
Build a lightweight SLAM system that runs on resource-constrained drone hardware for GPS-denied indoor navigation.
Why it matters
Indoor drones for warehouse inspection and emergency response need reliable localization without GPS. Current SLAM solutions are too computationally expensive for small drones.
Research gap
Existing visual-inertial SLAM systems require GPU acceleration that lightweight drones cannot provide.
Research questions
- 01 Can we achieve sub-10cm accuracy with only IMU + monocular camera?
- 02 How much can we compress the map representation without losing loop closure?
- 03 What is the minimum compute requirement for real-time operation?
Suggested technologies
Required skills
Team and supervisor
2-3 researchers, supervised by Muhammad Qasim.
Suitable for: Robotics, CS, AI.
Expected deliverables
- Lightweight SLAM implementation in C++
- Comparison paper against ORB-SLAM3 on drone benchmarks
- Flight test dataset with ground truth
Work on this problem
Apply to the lab and this problem becomes your supervised research project.