OpenClaw AI Rock-Paper-Scissors Tutorial

Before starting, please complete the [01-Hardware Configuration], [02-openclaw API-KEY Configuration], [03-openclaw Model Switching], [04-AI Voice Interaction Configuration], [05-Three Dialogue Solution Configuration Tests] under the Prerequisites directory. If you are currently only using TUI / whatsapp, you can skip 04 for now. This article assumes the basic environment has been prepared and only expands on the AI rock-paper-scissors project itself.

1. Tutorial Objectives

This article demonstrates OpenClaw's interactive gaming capability through "gesture recognition + AI referee + screen and light feedback". After completing this tutorial, readers can:

• Understand how to use the camera to recognize player gestures

• Communicate with OpenClaw through three methods: whatsapp, TUI, and voice code

• Complete four project scenarios: gesture recognition, AI move, result judgment, and score feedback

2. Hardware Preparation

• OpenClaw mainboard

• CSI camera module

• OLED display

• RGB light strip / RGB light bead module

• [Optional] AI voice module + speaker

• Wiring diagram

3. Software Preparation

Code entry points that will be used in the tutorial

• Camera capture command: /home/jetson/hardware_hal_demo/seewhat

• Voice entry: /home/jetson/voice_to_openclaw/src/main.py

The key capabilities of this project mainly consist of three parts:

• The camera is responsible for capturing player gestures

• OpenClaw is responsible for deciding AI's move and displaying the result on OLED / RGB

4. Test Basic Project Capabilities

Before starting the current project, please complete a openclaw tui basic dialogue self-check first; if you haven't done so, please refer to [05-Three Dialogue Solution Configuration Tests]. After passing, use TUI to verify the basic capabilities in the project.

Enter in terminal:

openclaw tui

Then you can do a few basic tests:

• Take a gesture photo for me

• Identify whether this is a peace sign

• Display "Ready" on OLED

• Light up the RGB in blue

5. Three Dialogue Solutions with OpenClaw

If you have opted for the AI voice module + speaker, and whatsapp dialogue, TUI, or WhatsApp dialogue needs to broadcast OpenClaw's reply content, you can run the following program in the terminal. AI voice module dialogue does not need to run this repeatedly

• Modify the parameter for enabling/disabling broadcast

xxxxxxxxxx
/home/jetson/voice_to_openclaw/.env

xxxxxxxxxx
ENABLE_TTS=true  # This parameter controls whether to broadcast. After modification, save and run the following command in terminal

• Enter in terminal

xxxxxxxxxx
cd ~/voice_to_openclaw
source .venv/bin/activate
python -m src.openclaw_session_tts

5.1 whatsapp Solution

For whatsapp integration and bot creation steps, please refer directly to [05-Three Dialogue Solution Configuration Tests]. After setup, you can remotely trigger the rock-paper-scissors game in WhatsApp, for example:

• Please play rock paper scissors. Take a photo to recognize my gesture. You can randomly make a gesture. Then judge whether you win or I win OLED displays who this round

You can add your own whatsapp conversation screenshots here.

5.2 TUI Solution

If you have completed the TUI self-check in the prerequisites, directly enter terminal text dialogue:

xxxxxxxxxx
openclaw tui

Then enter project-related commands, for example:

• Let's play rock paper scissors game. First you randomly make a gesture. Then take a photo to recognize my gesture. Finally judge whether you win or I win. OLED displays who won this round. If you win, light up the flowing light; if I win, make the servo dance

5.3 Voice Code Solution

xxxxxxxxxx
Requires the optional AI voice interaction module + speaker

For voice module installation, environment configuration, and basic wake-up process, please refer directly to [04-AI Voice Interaction Configuration]. After wake-up, you can directly speak the control content, for example:

• Let's play rock, paper, scissors, take a photo to recognize my gesture. You can randomly make a gesture then judge whether you win or I win.

6. Project Implementation

Note: The following demonstrations are all done through openclaw tui dialogue. You can also choose whatsapp or voice methods to complete them.

6.1 Scenario 1: Gesture Recognition

Experiment Objective

Recognize the player's current gesture, such as rock, paper, or scissors.<