GPS-Denied Autonomous Drone Design
Budget: ₹37,500 – ₹75,000 INR
I am building a drone that must hold position and navigate stably even when no satellite signal is available. The heart of the project is a robust Visual Positioning System; everything else—INS, SLAM, LiDAR depth cues—supports that goal. My preferred camera setup is both a forward- and downward-facing RGB/IR feed so the craft can reference ground texture while also “seeing” obstacles ahead.
Here is what I need from you, all to be wrapped up within the next month:
• Hardware-ready system architecture: clear wiring, power budgeting, and mounting plan for the IMU, dual cameras, optional LiDAR, onboard NVIDIA Jetson/PI-class edge computer, and solid-state map storage.
• Sensor-fusion software stack (ROS2 or comparable), fusing visual odometry, IMU data and any depth returns to output reliable pose estimates at 30 Hz +.
• VPS-centred navigation module that can lock a hover inside a 10×10 m indoor test area and follow simple waypoints without drift.
• Flight-ready firmware configuration for PX4/ArduPilot (your choice) plus any custom nodes or plugins.
• Demonstration: recorded indoor flight or live log proving sub-0.5 m position error over a two-minute hover and successful 360° yaw without loss of tracking.
• Full deliverables set: commented source code, build instructions, BOM, CAD/placement drawings, and short PDF report explaining algorithms and tuning parameters.
If feasible assistance in building the full drone
If you have a track record with vision-based navigation, SLAM, OpenCV, and real-time sensor fusion on resource-constrained hardware, I’d love to see how you can make this drone fly where GPS can’t reach.
Here is what I need from you, all to be wrapped up within the next month:
• Hardware-ready system architecture: clear wiring, power budgeting, and mounting plan for the IMU, dual cameras, optional LiDAR, onboard NVIDIA Jetson/PI-class edge computer, and solid-state map storage.
• Sensor-fusion software stack (ROS2 or comparable), fusing visual odometry, IMU data and any depth returns to output reliable pose estimates at 30 Hz +.
• VPS-centred navigation module that can lock a hover inside a 10×10 m indoor test area and follow simple waypoints without drift.
• Flight-ready firmware configuration for PX4/ArduPilot (your choice) plus any custom nodes or plugins.
• Demonstration: recorded indoor flight or live log proving sub-0.5 m position error over a two-minute hover and successful 360° yaw without loss of tracking.
• Full deliverables set: commented source code, build instructions, BOM, CAD/placement drawings, and short PDF report explaining algorithms and tuning parameters.
If feasible assistance in building the full drone
If you have a track record with vision-based navigation, SLAM, OpenCV, and real-time sensor fusion on resource-constrained hardware, I’d love to see how you can make this drone fly where GPS can’t reach.