How to control your 🚁 drone using #ChatGPT

Hi!

I’ve been doing live demos of how to use Azure OpenAI Services or OpenAI APIs to generate code to control the drone, so I think I may write about it to have it public for future references.

So, using the base code to send and read drone information, we can create a simple prompt like this one:

Use this python code as reference 

[CODE START]
# display battery level
sendReadCommand('battery?')
print(f'Battery: {battery} %')

# take off
sendCommand("takeoff") 

# flip the drone left
sendCommand("flip l") 

# move drone up 5 cms
sendCommand("up 5") 

# move drone left 5 cms
sendCommand("left 5") 

# rotate drone clock wise 90 degrees
sendCommand("cw 90") 

# land the drone
sendCommand("land") 

[CODE END]

Generate code to takeoff the drone, flip right, move down 30 centimeters and land

If we are working with GPT models, we can test this in ChatGPT.

GPT model completion is incredibly good. It generates the necessary commands, and it also infers new commands like flip right or move in a different direction.

If you have seen my demos, you remember me complaining about UDP. And knowing that this drone is a toy plus the UDP challenge, it may make sense to add a 5 second delay between commands.

ChatGPT updates the generated code, adding a time.sleep(5) instruction after each command.

So far, so good. We can copy the generated code and make our drone fly.

In the next post we will automate this code generation using Azure OpenAI Services or OpenAI APIs.