Yes but in my experience, LLMs are prone to cheating and implementing "shortcuts" that look functional but are in fact not really if you look closely. At the moment, you still need a human in the loop to make sure the LLM actually did what it promised and didn't cheat.
1. Camera captures video
2. Neural network recognizes pigeon
3. Watergun turns toward pigeon
4. Spray pigeon with watergun
Components:
* Electric battery-driven water gun (disassembled, orange)
* USB camera
* Orange Pi 5
* 2 servo motors (SG90 or MG90S)
* Resistors and a transistor for turning on the watergun (e.g. IRLZ44N)
It uses an open vocabulary object detection neural network (yolo_world_v2l), so any target can be programmed, not just pigeons. Runs on the Rockchip 3588's Neural Processing Unit.