← 返回 Skills 市场

JAKA Robotics Control Skill

Name: JAKA Robotics Control Skill
Author: qujingyang28

作者 Robot_Qu · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

254

总下载

当前安装

版本数

在 OpenClaw 中安装

/install jaka-robotics-control

功能描述

Control Zu20/Zu12/Zu7 collaborative robots via gRPC/TCP with joint, linear, and circular motion, real-time state monitoring, and simulation support.

使用说明 (SKILL.md)

JAKA Robotics Control Skill

节卡机器人控制技能，支持 Zu20/Zu12/Zu7/MiniCobo 全系列协作机器人。

功能特性

✅ 关节运动控制
✅ 直线运动控制
✅ 状态读取
✅ 末端工具 I/O 控制
✅ gRPC 通信（低延迟、高可靠）

快速开始

1. 安装 JAKA SDK

pip install jaka-sdk

或访问 JAKA 官网下载： https://www.jaka.com/docs/guide/SDK/introduction.html

2. 配置机器人 IP

编辑 jaka_cmd.py，修改：

ROBOT_IP = "192.168.57.128"  # 改成你的 MiniCobo IP

3. 使用 Python API

from jaka_skill import JAKARobot

robot = JAKARobot("192.168.57.128", use_grpc=True)
robot.connect()

# 关节运动 (弧度)
robot.move_joint([0, 0, 0, 0, 0, 0], speed=0.5)

# 直线运动 (mm, rad)
robot.move_linear([300, 0, 200, 3.14, 0, 0], speed=100)

# 读取状态
state = robot.get_state()
print(state['joints_deg'])

robot.disconnect()

4. 命令行工具

# 读取状态
python jaka_cmd.py state

# 回零
python jaka_cmd.py home

# 关节运动 (角度)
python jaka_cmd.py joint 90 90 90 90 90 90

# 直线运动 (mm, 度)
python jaka_cmd.py linear 300 0 200 180 0 0

支持机型

JAKA Zu20（实验室主力）
JAKA Zu12
JAKA Zu7
JAKA MiniCobo（本技能测试机型）

环境要求

Python 3.8+
JAKA SDK V2.3.1+
Windows

安全提示

⚠️ 首次使用前请确保：

工作空间内无人
急停按钮可用
先在低速环境测试
T1 模式调试

作者

JMO / Robotqu (青岛)

网站：robotqu.com
B 站：Robot_Qu 机器人社区

许可证

MIT-0

安全使用建议

This skill appears to be what it claims: a thin Python wrapper around the JAKA SDK. Before installing or using it, verify the source of the JAKA SDK and the pip package (use the official JAKA website links shown), and only copy native binaries (jkrc.pyd, jakaAPI.dll) obtained from the vendor. Set the robot IP to a local, isolated network address and do not expose robot control to the public Internet. Follow the listed physical safety steps (empty workspace, e-stop, low-speed testing). If you are unsure about the pip package name or the downloaded SDK, obtain SDK binaries directly from JAKA support or your robot vendor and inspect them in a secure environment first.

功能分析

Type: OpenClaw Skill Name: jaka-robotics-control Version: 1.0.1 The skill is a legitimate wrapper for the JAKA Robotics SDK, providing tools to control Zu and MiniCobo series robots via gRPC. It includes a CLI (jaka_cmd.py) and a core library (jaka_skill.py) that interact with the robot hardware using the official 'jkrc' library. No malicious behavior, data exfiltration, or prompt injection attempts were detected, and the documentation includes appropriate safety warnings for physical hardware operation.

能力评估

✓ Purpose & Capability

The name/description claim (control JAKA Zu/MiniCobo robots via SDK) matches the included Python wrapper and CLI (jaka_skill.py, jaka_cmd.py, example). The files call the expected jkrc SDK functions (login, joint_move, linear_move_extend) and the README/SKILL.md document the required native SDK artifacts—so required artifacts are explainable by the stated purpose.

✓ Instruction Scope

Runtime instructions only cover installing the JAKA SDK, setting the robot IP, and running the provided Python scripts. The SKILL.md does not instruct reading unrelated files, leaking secrets, or contacting unexpected endpoints. It does ask the user to place vendor SDK binaries (jkrc.pyd, jakaAPI.dll) into the skill directory, which is necessary for the native SDK but worth noting.

ℹ Install Mechanism

There is no automated install spec; users are told to pip install jaka-sdk or download the SDK from the vendor and copy jkrc.pyd/jakaAPI.dll into the skill folder. This is expected for native-extension SDKs but carries the usual trust risk of installing native binaries or an unverified pip package—verify the package and vendor site before installing.

✓ Credentials

The skill requires no environment variables, credentials, or config paths. It requires network access to a local robot IP (user-provided). No unrelated secrets or service tokens are requested.

✓ Persistence & Privilege

The skill does not request always:true, does not modify other skills or system-wide settings, and is user-invocable only. It does ask the user to copy SDK binaries into the skill workspace (normal for native SDK usage) but does not attempt to persist credentials or enable autonomous privileged behavior.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install jaka-robotics-control
安装完成后，直接呼叫该 Skill 的名称或使用 /jaka-robotics-control 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.1

- Expanded supported models to include JAKA MiniCobo and updated documentation accordingly. - Added multiple new example and test scripts for linear, joint, and circular movements. - Integrated JAKA SDK installation instructions and simplified setup steps. - Removed outdated demo scripts to focus on direct API usage and testing. - Improved feature list and clarified safe operation guidelines in documentation.

v1.0.0

JAKA Robotics Control Skill 1.0.0 – Initial Release - Supports motion control for JAKA Zu20/Zu12/Zu7 collaborative robots. - Features precise joint and linear motion, arc interpolation, and real-time status monitoring. - Includes both gRPC and TCP communication modes, simulation synchronization, and a command-line tool. - Provides demonstration scripts for various movements and tasks. - Requires Python 3.8+, JAKA SDK V2.3.1+, and Windows environment.

元数据

Slug jaka-robotics-control

版本 1.0.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题