** Autonomous targetted deep stall landing of a UAV
*** Key differentiator
+ Current techniques for deep stall landing lack accurate air speed and angle of attack estimation at high alpha (angle of attack).
+ Using [[file:aerodynamic-state-and-loads-estimation-using-bioinspired-distributed-sensing.pdf][biomimicry some authors have demonstrated]] the ability to accurately estimate air speed and alpha at high alpha.
Using a distributed pressure sensor array of pressure sensors and a neural network we will accurately estimate angle of attack and air speed for targetted autonomous deep stall landing
*** Research
Summarize the exisitng research here.
* Action Items
+ [X] Add sean to matrix ::Reg::
+ [ ] Add codeberg for file storage/collaboration ::Reg::
+ [ ] Come up with integration plan for sensors, NN, and PX4 board
+ [ ] Come up with NN training plan and target hardware
Literature Review and Research: Begin by thoroughly understanding the two papers and any other relevant research. This will help you understand the current state of the art and identify any gaps or challenges that need to be addressed.
Project Planning: Define the scope of your project, establish your objectives, and create a timeline. Identify the resources you'll need, such as hardware components, software tools, and personnel with the necessary skills.
Hardware Acquisition and Setup: Acquire the necessary hardware components for your drone, including the airframe, motors, control systems, and distributed pressure sensors. You'll also need to consider how to integrate the sensors into the drone in a way that allows them to effectively measure airspeed and angle of attack.
Sensor Integration and Calibration: Integrate the sensors with the drone's control system. You'll need to calibrate the sensors to ensure they provide accurate data.
AI Model Development: Develop an AI model that can interpret the sensor data and determine the drone's airspeed and angle of attack. This will likely involve training a machine learning model using a dataset of sensor readings and corresponding airspeeds and angles of attack.
Control System Development: Develop a control system that can use the AI model's output to control the drone's flight. This will likely involve developing algorithms that can adjust the drone's flight based on the detected airspeed and angle of attack.
Testing and Iteration: Conduct extensive testing to ensure the system works as expected. This will likely involve both simulated tests and real-world flight tests. Use the results of these tests to iteratively improve your system.
Performance Evaluation: Once you've refined your system, conduct a final evaluation to assess its performance. This could involve comparing its performance to that of a drone without your system, or assessing its ability to maintain stable flight in various conditions.
Documentation and Reporting: Document your work thoroughly, including your methods, results, and any challenges you encountered. This will be important if you want to publish your work or use it as the basis for future projects.
Project Review and Future Work: Review the project outcomes against the initial objectives. Identify any areas for future work or improvement.
