AI Chat Integration with all WebTools¶ Skills required: JavaScript, OpenAI, Google Gemini

Mentor: Randy Mackay

Expected Size: 175h

Level of Difficulty: Medium

Expected Outcome: All WebTools include AI chat to help users understand and use the tool

This project involves adding an OpenAI or Google Gemini chat window into some or all of the ArduPilot Webtools

Once complete some or all of the WebTools should:

Include a new chat widget allowing users to ask an AI assistant questions about the tool using text or voice

Allow the AI assistant to operate the tool based on user input (e.g. push buttons, change zoom of graphs, etc)

The top priority WebTool is the “UAV Log viewer” although simpler tools like the “Hardware Report” could be a good starting point

Most of the development can be completed using the SITL simulator and any OpenAI or Google Gemini usage costs will be covered

ArduPilot Web Tools A number of web-based tools for ArduPilot log and parameter review. These tools operate on the client side, no data is uploaded to any server at any time. Many of the tools have a "Open In" button, this allows a log that has been opened in one tool to be transferred to another, the selected tool will be opened in a new tab and the log loaded.

Log Finder A tool load and sort directories of logs. Note that directory read is not supported by all browsers. Logs are sorted by the unique hardware ID of the flight controller. Parameter changes are tracked between logs. Open in links allow files to be easily opened in any of the other tools.

UAV Log viewer General purpose ArduPilot log review with 3D flight visualization.

Hardware Report Provides a overview of connected hardware from a parameter file or log. If a log is used more information can be provided, such as sensor health status and exact firmware version. A range of options are available to extract parameters from logs, all, only changed or minimal removing calibration parameters. Includes visualization for sensor position offsets.

MAGFit Calibrate compass from flight log. This tool fits the logged magnetometer data to the world magnetic model providing offsets, iron correction, scale, motor compensation and checking orientation.

Filter Review Gyro noise and filter configuration tool. Uses raw or batch IMU logs to show the vehicles noise profile. Filters can are applied logged pre-filter data to see the effect without the need to fly again.

PID Review Review PID tune in the frequency domain. Step response estimate is generated. Results are split based on parameter changes.

Filter Tool Bode plot tool to give insight into gyro low pass and notch filter setup. This tool visualizes the attenuation and phase lag of a filter setup loaded from a parameter file. For filter setup the FilterReview tool it is recommended it provides the same bode plot feedback. This filter tool allows the attenuation and phase lag of each filter to be plotted individually, something which the filter reivew tool cannot do. This tool also provides a estimated response for the rate PID gains.

Work in progress tools The tools that are a work in progress, they are likely to be a little rough.

SITL Simulator (Software in the Loop)¶ ../_images/sitl.jpg The SITL (software in the loop) simulator allows you to run Plane, Copter or Rover without any hardware. It is a build of the autopilot code using an ordinary C++ compiler, giving you a native executable that allows you to test the behaviour of the code without hardware.

This article provides an overview of SITL’s benefits and architecture.

Overview¶ SITL allows you to run ArduPilot on your PC directly, without any special hardware. It takes advantage of the fact that ArduPilot is a portable autopilot that can run on a very wide variety of platforms. Your PC is just another platform that ArduPilot can be built and run on.

When running in SITL the sensor data comes from a flight dynamics model in a flight simulator. ArduPilot has a wide range of vehicle simulators built in, and can interface to several external simulators. This allows ArduPilot to be tested on a very wide variety of vehicle types. For example, SITL can simulate:

multi-rotor aircraft

fixed wing aircraft

ground vehicles

underwater vehicles

camera gimbals

antenna trackers

a wide variety of optional sensors, such as Lidars and optical flow sensors

Adding new simulated vehicle types or sensor types is straightforward.

A big advantage of ArduPilot on SITL is it gives you access to the full range of development tools available to desktop C++ development, such as interactive debuggers, static analyzers and dynamic analysis tools. This makes developing and testing new features in ArduPilot much simpler.

Running SITL¶ The ArduPilot SITL environment has been developed to run natively on both Linux and Windows. For setup instructions see Setting Up SITL for more information. Using SITL is explained in Using SITL. For examples of starting and using SITL for a particular vehicle see Examples of using SITL by Vehicle.

Mission Planner (Windows) also provides a simple means of running SITL for the master branch and stable branches of vehicles. See Mission Planner Simulation.

SITL Architecture¶ Note in the image below the port numbers are indicative only and can vary. For instance the ports between ArduPilot and the simulator on the image are 5501/5502 but they can vary to be 5504/5505 or other port numbers depending on your environment.

now make a gsoc proposal for this org reference if given for my pal proposal do not include prelimaary work and give latex for this proposal in a good way with solution and add all my details as given in the pal proposal give final latex