Agent Skill 用于通过 rosbridge WebSocket 控制 ROS/ROS2 机器人。
概览
Agent Skill 用于通过 rosbridge WebSocket 控制 ROS/ROS2 机器人。 一个人工智能代理技能,使代理通过自然语言控制ROS机器人。代理读取 SKILL.md,理解可用命令,并通过rosbridge执行ros_cli.py与任何ROS/ROS2系统交互。 直接从命令行ros_cli.py。 可与任何支持代理技能的AI代理配合使用。为了方便设置,我们推荐OpenClaw——从ClawHub安装并与你的机器人对话: - “连接ROS机器人” - “将机器人前移1米” - “有哪些主题可用?” 完整设置和使用方法请参见OpenClaw教程。 所有命令输出 JSON。详见 SKILL.md 快速参考和参考/COMMANDS.md 以获取完整细节及输出示例。 1. 代理平台将 SKILL.md 加载到代理的系统提示符中 2.命令中的{baseDir}被实际的技能安装路径取代 3.用户请求类似“推动机器人前进”的请求 4.代理执行:python {baseDir}/scripts/ros_cli。
概述(AI 翻译)
Agent Skill 用于通过 rosbridge WebSocket 控制 ROS/ROS2 机器人。
概述
一种人工智能代理技能,使代理通过自然语言控制ROS机器人。代理读取SKILL.md,理解可用命令,并执行ros_cli.py,通过rosbridge与任何ROS/ROS2系统交互。
快速启动(CLI)
直接从命令行使用ros_cli.py。
快速启动(AI代理)
ros-skill 可与任何支持 Agent Skills 的 AI 代理配合使用。为了方便设置,我们推荐 OpenClaw——从 ClawHub 安装 ros-skill 并与你的机器人对话:
- “连接ROS机器人”
- “将机器人前移1米”
- “有哪些主题可用?”
完整设置和使用方法请参见OpenClaw教程。
支持的指令
| 类别 | 命令 |
|---|---|
| 连接 | connect, version |
| 主题 | list、type、details、message、subscribe、publish、publish-sequence |
| 服务 | list, type, details, call |
| 节点 | list, details |
| 参数 | list, get, set(仅限ROS 2) |
| 操作 | list, details, send(仅限ROS 2) |
所有命令均输出 JSON。请参见 SKILL.md 快速参考和“references/COMMANDS”。
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
ROS Skill
Agent Skill for ROS/ROS2 robot control via rosbridge WebSocket.
Agent (LLM) → ros_cli.py → rosbridge (WebSocket :9090) → ROS/ROS2 Robot
Overview
An AI agent skill that lets agents control ROS robots through natural language. The agent reads SKILL.md, understands available commands, and executes ros_cli.py to interact with any ROS/ROS2 system via rosbridge.
Quick Start (CLI)
Use ros_cli.py directly from the command line.
# Install
pip install websocket-client
# Launch rosbridge on the robot (ROS 2)
sudo apt install ros-${ROS_DISTRO}-rosbridge-server
ros2 launch rosbridge_server rosbridge_websocket_launch.xml
# Connect
python scripts/ros_cli.py connect
# Explore
python scripts/ros_cli.py topics list
python scripts/ros_cli.py nodes list
# Move robot forward for 3 seconds
python scripts/ros_cli.py topics publish /cmd_vel geometry_msgs/Twist \
'{"linear":{"x":1.0,"y":0,"z":0},"angular":{"x":0,"y":0,"z":0}}' --duration 3
# Read sensor data
python scripts/ros_cli.py topics subscribe /scan sensor_msgs/LaserScan --timeout 3
Quick Start (AI Agent)
ros-skill works with any AI agent that supports Agent Skills. For easy setup, we recommend OpenClaw — install ros-skill from ClawHub and talk to your robot:
- “Connect to the ROS robot”
- “Move the robot forward 1 meter”
- “What topics are available?”
See the OpenClaw tutorial for full setup and usage.
Supported Commands
| Category | Commands |
|---|---|
| Connection | connect, version |
| Topics | list, type, details, message, subscribe, publish, publish-sequence |
| Services | list, type, details, call |
| Nodes | list, details |
| Parameters | list, get, set (ROS 2 only) |
| Actions | list, details, send (ROS 2 only) |
All commands output JSON. See SKILL.md for quick reference and references/COMMANDS.md for full details with output examples.
How It Works
- The agent platform loads
SKILL.mdinto the agent’s system prompt {baseDir}in commands is replaced with the actual skill installation path- User asks something like “move the robot forward”
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add lpigeon/ros-skill