kuavo-humanoid-sdk 0.1.2__tar.gz → 1.1.2a921__tar.gz

kuavo_humanoid_sdk-1.1.2a921/PKG-INFO

@@ -0,0 +1,271 @@
+Metadata-Version: 2.1
+Name: kuavo_humanoid_sdk
+Version: 1.1.2a921
+Summary: A Python SDK for kuavo humanoid robot.
+Home-page: https://gitee.com/leju-robot/kuavo-ros-opensource/
+Author: ['lejurobot']
+Author-email: edu@lejurobot.com
+License: MIT
+Project-URL: Documentation, https://gitee.com/leju-robot/kuavo-ros-opensource/
+Project-URL: Source Code, https://gitee.com/leju-robot/kuavo-ros-opensource/
+Keywords: kuavo,humanoid,robot,robotics,lejurobot,ros
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# Kuavo Humanoid SDK
+
+A comprehensive Python SDK for controlling Kuavo humanoid robots. This SDK provides interfaces for robot state management, arm and head control, and end-effector operations. It is designed to work with ROS (Robot Operating System) environments.
+
+**Warning**: This SDK currently only supports **ROS1**. ROS2 support is not available.
+
+**Warning**: **This SDK can only be used on the onboard NUC computer located in the robot's torso.** 
+
+![Kuavo 4Pro Robot](https://kuavo.lejurobot.com/manual/assets/images/kuavo_4pro-cf84d43f1c370666c6e810d2807ae3e4.png)
+
+## Features
+
+- Robot State Management
+  - IMU data (acceleration, angular velocity, euler angles)
+  - Joint/motor states (position, velocity, torque)
+  - Torso state (position, orientation, velocity)
+  - Odometry information
+  - End-effector states:
+    - Gripper(lejuclaw): position, velocity, torque, grasp status
+    - Dexterous hand(qiangnao): position, velocity, torque
+    - Touch Dexterous hand(qiangnao_touch): position, velocity, torque, touch state
+    - End-effector position and orientation
+  - Motion states: stand, walk, step_control, trot
+
+- Motion Control
+  - Arm Control
+    - Joint position control
+    - End-effector 6D control via inverse kinematics
+    - Forward kinematics (FK) for computing end-effector pose
+    - Keyframe sequence control for complex motions
+  - End-effector Control
+    - Gripper control (position control with configurable velocity and torque)
+    - Dexterous hand control
+      - Position control
+      - Pre-defined hand gestures (OK, 666, fist, etc.)
+  - Head Control
+    - Position control
+  - Torso Control
+    - Height control (squatting)
+    - Forward/backward tilt control
+  - Dynamic Motion Control
+    - Stance
+    - Trot
+    - Walking (xy and yaw velocity control)
+    - Stepping (gait switching)
+
+- Robot Basic Information
+  - Robot type (kuavo)
+  - Robot version
+  - End-effector type
+  - Joint names
+  - Total degrees of freedom (28)
+  - Arm degrees of freedom (7 per arm)
+  - Head degrees of freedom (2)
+  - Leg degrees of freedom (12)
+
+## Installation
+
+**Note: There are currently two versions of this SDK, the stable version and the beta version. Their differences are:**
+
+- stable version: corresponding to the functionality provided by the `master` branch of [kuavo-ros-opensource](https://gitee.com/leju-robot/kuavo-ros-opensource/).
+- Beta version: This version is more aggressive than the official version and also provides richer functionality, corresponding to the functionality provided by the `beta` branch of [kuavo-ros-opensource](https://gitee.com/leju-robot/kuavo-ros-opensource/).
+
+**Friendly reminder: Please be clear about which version you need to install. If your SDK version does not match `kuavo-ros-opensource`, some features may not be available.**
+
+Install the latest **​stable version** of Kuavo Humanoid SDK using pip:
+```bash
+pip install kuavo-humanoid-sdk  
+```
+
+Install the latest **​beta version** of Kuavo Humanoid SDK using pip:
+```bash
+pip install --pre kuavo-humanoid-sdk  
+```
+
+For local development installation (editable mode), use:
+```bash
+cd src/kuavo_humanoid_sdk  
+chmod +x install.sh  
+./install.sh   
+```
+## Upgrade Instructions
+Before upgrading, you can check the currently installed version with:
+```bash
+pip show kuavo-humanoid-sdk  
+# Output:  
+Name: kuavo-humanoid-sdk  
+Version: 0.1.2  
+...  
+```
+
+**Note: If the version number contains the letter b, it indicates a beta version, e.g., Version: 0.1.2b113**
+
+To upgrade from a stable version to the latest stable version:
+```bash
+pip install --upgrade kuavo_humanoid_sdk  
+```
+
+To upgrade from a beta version to the latest stable version:
+```bash
+pip install --upgrade --force-reinstall kuavo_humanoid_sdk  
+# or  
+pip uninstall kuavo_humanoid_sdk && pip install kuavo_humanoid_sdk  
+```
+
+To upgrade from a stable/beta version to the latest beta version:
+```bash
+pip install --upgrade --pre kuavo_humanoid_sdk  
+```
+
+## Package Information
+
+You can check the package information using pip:
+```bash
+pip show kuavo-humanoid-sdk
+```
+
+## Quick Start
+
+Here's a simple example to get started with Kuavo Humanoid SDK:
+
+> **Warning**: Before running any code, make sure to start the robot first by executing either:
+> - For simulation: `roslaunch humanoid_controllers load_kuavo_mujoco_sim.launch` (Example command)
+> - For real robot: `roslaunch humanoid_controllers load_kuavo_real.launch` (Example command)
+```python3
+# Copyright (c) 2025 Leju Robotics. Licensed under the MIT License.
+import time
+from kuavo_humanoid_sdk import KuavoSDK, KuavoRobot
+
+def main():
+    if not KuavoSDK().Init():  # Init! !!! IMPORTANT !!!
+        print("Init KuavoSDK failed, exit!")
+        exit(1)
+    robot = KuavoRobot()    
+    
+    """ arm reset """
+    print("Switching to arm reset mode...")
+    robot.arm_reset()
+    
+    """ stance """
+    print("Switching to stance mode...")
+    robot.stance()
+
+    """ trot """
+    print("Switching to trot mode...")
+    robot.trot()
+    
+    """ walk forward """
+    print("Starting forward walk...")
+    duration = 4.0  # seconds
+    speed = 0.3     # m/s
+    start_time = time.time()
+    while (time.time() - start_time < duration):
+        robot.walk(linear_x=speed, linear_y=0.0, angular_z=0.0)
+        time.sleep(0.1)  # Small sleep to prevent busy loop
+    
+if __name__ == "__main__":
+    main()
+```
+
+## Docs
+The documentation is available in two formats:
+- HTML format: [docs/html](docs/html), **needs to be generated by running the script**
+- Markdown format: [docs/markdown](docs/markdown)
+
+We recommend that you generate the documentation locally by running the documentation script. The documentation will be output to the `docs/html` and `docs/markdown` folders:
+```bash
+cd <kuavo-ros-opensource>/src/kuavo_humanoid_sdk
+chmod +x gen_docs.sh
+./gen_docs.sh
+```
+
+**We recommend that you view the documentation using `html` for a better experience.**
+
+For Markdown documentation at:
+
+https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/docs/markdown/index.md
+
+## Examples
+
+#### WARNING
+Before running any code examples, make sure to start the robot first by executing either:
+
+- For simulation: `roslaunch humanoid_controllers load_kuavo_mujoco_sim.launch` (Example command)
+- For real robot: `roslaunch humanoid_controllers load_kuavo_real.launch` (Example command)
+
+### Robot Info
+
+Examples showing how to get basic robot information.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/robot_info_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/robot_info_example.py)
+
+### Basic Robot Control
+
+A basic example showing how to initialize the SDK and control the robot’s movement.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/motion_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/motion_example.py)
+
+### End Effector Control
+
+#### LejuClaw Gripper
+
+Examples demonstrating how to control the LejuClaw gripper end effector, including position, velocity and torque control.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/lejuclaw_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/lejuclaw_example.py)
+
+#### QiangNao DexHand
+
+Examples showing how to control the QiangNao DexHand, a dexterous robotic hand with multiple degrees of freedom for complex manipulation tasks.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/dexhand_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/dexhand_example.py)
+
+### Arm Control
+
+Examples showing arm trajectory control and target pose control.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/ctrl_arm_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/ctrl_arm_example.py)
+
+### Forward and Inverse Kinematics
+
+Examples demonstrating how to use forward kinematics (FK) to compute end-effector positions from joint angles, and inverse kinematics (IK) to calculate joint angles needed to achieve desired end-effector poses.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/arm_ik_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/arm_ik_example.py)
+
+### Head Control
+
+Examples showing how to control the robot’s head movements, including nodding (pitch) and shaking (yaw) motions.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/ctrl_head_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/ctrl_head_example.py)
+
+### Step-by-Step Control
+
+Examples showing how to control the robot’s movements step by step, including individual foot placement and trajectory control.
+
+[https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/step_control_example.py](https://gitee.com/leju-robot/kuavo-ros-opensource/tree/master/src/kuavo_humanoid_sdk/examples/step_control_example.py)
+
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contact & Support
+
+For any questions, support, or bug reports, please contact:
+- Email: edu@lejurobot.com
+- Website: https://gitee.com/leju-robot/kuavo-ros-opensource/
+- Source Code: https://gitee.com/leju-robot/kuavo-ros-opensource/
+- Issue Tracker: https://gitee.com/leju-robot/kuavo-ros-opensource/issues

kuavo_humanoid_sdk-1.1.2a921/README.md

@@ -0,0 +1,78 @@
+# Kuavo Humanoid SDK
+[![Version](https://img.shields.io/pypi/v/kuavo-humanoid-sdk.svg)](https://pypi.org/project/kuavo-humanoid-sdk/)[![License](https://img.shields.io/pypi/l/kuavo-humanoid-sdk.svg)](#)[![Supported Python Versions](https://img.shields.io/pypi/pyversions/kuavo-humanoid-sdk.svg)](https://pypi.python.org/pypi/kuavo-humanoid-sdk)
+
+一个全面的 Python SDK，用于控制 Kuavo 人形机器人。该 SDK 提供了机器人状态管理、手臂和头部控制以及末端执行器操作的接口。它设计用于与 ROS（机器人操作系统）环境一起工作。
+
+**警告**：该 SDK 目前仅支持 **ROS1**。不支持 ROS2。
+
+PyPI 项目地址: https://pypi.org/project/kuavo-humanoid-sdk/
+
+## 安装
+**提示：对于本 SDK 目前存在两个版本，正式发布版与beta内测版, 他们的区别是：**
+- 正式发布版：稳定版，对应[kuavo-ros-opensource](https://gitee.com/leju-robot/kuavo-ros-opensource/)的`master` 分支提供的功能，
+- beta内测版：该版本较正式版会激进一些，同时也会提供更丰富的功能，对应[kuavo-ros-opensource](https://gitee.com/leju-robot/kuavo-ros-opensource/)的`beta` 分支提供的功能。
+
+**温馨提示：请务必明确您需要安装的版本，如果您的SDK版本与`kuavo-ros-opensource`未匹配，可能会出现某些功能不可用的错误。**
+
+安装最新的**正式版** Kuavo Humanoid SDK，可以使用 pip：
+```bash
+pip install kuavo-humanoid-sdk
+```
+
+安装最新的**beta版** Kuavo Humanoid SDK，可以使用 pip：
+```bash
+pip install --pre kuavo-humanoid-sdk
+
+```
+对于本地开发安装（可编辑模式），请使用：
+```bash
+cd src/kuavo_humanoid_sdk
+chmod +x install.sh
+./install.sh
+```
+
+## 升级更新
+
+在升级更新之前，您可以先执行以下命令来查看当前安装的版本：
+```bash
+pip show kuavo-humanoid-sdk
+# Output:
+Name: kuavo-humanoid-sdk
+Version: 0.1.2
+...
+```
+**提示：如果您的版本号中包含字母`b`，则表示该版本为测试版, 比如`Version: 0.1.2b113`**
+
+**当前为正式版**，升级到最新正式版:
+```bash
+pip install --upgrade kuavo_humanoid_sdk
+```
+**当前为beta版**，升级到最新正式版:
+```bash
+pip install --upgrade --force-reinstall kuavo_humanoid_sdk
+# 或者
+pip uninstall kuavo_humanoid_sdk && pip install kuavo_humanoid_sdk
+```
+**当前为正式版/beta版**，升级到最新beta版:
+```bash
+pip install --upgrade --pre kuavo_humanoid_sdk
+```
+
+## 描述
+
+有关详细的 SDK 文档和使用示例，请参阅 [sdk_description.md](sdk_description.md)。
+
+## 文档
+文档提供两种格式：
+- HTML 格式：[docs/html](docs/html), **需要自己执行脚本生成**
+- Markdown 格式：[docs/markdown](docs/markdown)
+
+我们推荐您自己执行文档脚本生成文档到本地, 文档会输出到`docs/html`和`docs/markdown`文件夹:
+```bash
+chmod +x ./gen_docs.sh
+./gen_docs.sh
+```
+
+我们推荐您使用`html`查看文档更加方便，比如:
+![](docs/images/image.png)
+

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/__init__.py

@@ -1,3 +1,4 @@
+from .msg import *
 from .interfaces import *
 from .kuavo import *
 from kuavo_humanoid_sdk.common.logger import SDKLogger, disable_sdk_logging

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/interfaces/data_types.py

@@ -65,13 +65,13 @@ class EndEffectorState:
     """Data class representing the state of the end effector.
 
     Args:
-        position (float): Position of the end effector, [0, 100]
-        velocity (float): ...
-        effort (float): ...
+        position (list): float, Position of the end effector, range: [0, 100]
+        velocity (list): float, ...
+        effort (list): float, ...
     """
-    position: float
-    velocity: float
-    effort: float
+    position: list
+    velocity: list
+    effort: list
     class GraspingState(Enum):
         """Enum class representing the grasping states of the end effector.
 
@@ -119,4 +119,27 @@ class KuavoIKParams:
     # constraint and cost params
     oritation_constraint_tol: float = 1e-3
     pos_constraint_tol: float = 1e-3 # 0.001m, work when pos_cost_weight==0.0
-    pos_cost_weight: float = 0.0 # If U need high accuracy, set this to 0.0 !!!
+    pos_cost_weight: float = 0.0 # If U need high accuracy, set this to 0.0 !!!
+
+@dataclass
+class KuavoDexHandTouchState:
+    """Data class representing the touch state of the dexterous hand."""
+    
+    @dataclass
+    class KuavoTouchState:
+        """Data class representing the touch state of the dexterous hand."""
+        normal_force1: int  # 法向力1
+        normal_force2: int  # 法向力2
+        normal_force3: int  # 法向力3
+        tangential_force1: int  # 切向力1
+        tangential_force2: int  # 切向力2
+        tangential_force3: int  # 切向力3
+        tangential_direction1: int  # 切向力方向1
+        tangential_direction2: int  # 切向力方向2
+        tangential_direction3: int  # 切向力方向3
+        self_proximity1: int  # 自电容接近传感器1
+        self_proximity2: int  # 自电容接近传感器2
+        mutual_proximity: int  # 互电容接近传感器
+        status: int  # 传感器状态
+    # 5 fingers
+    data: Tuple[KuavoTouchState, KuavoTouchState, KuavoTouchState, KuavoTouchState, KuavoTouchState]

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/interfaces/end_effector.py

@@ -4,8 +4,27 @@ from kuavo_humanoid_sdk.interfaces.data_types import EndEffectorSide, EndEffecto
     
 class EndEffector(ABC):
     def __init__(self, joint_names: list):
-        self.joint_names = joint_names
+        self._joint_names = joint_names
+
+    def joint_names(self)->list:
+        """Returns the joint names of the end effector.
+        
+        Returns:
+            list: The joint names of the end effector.
+        """
+        return self._joint_names
+    
+    def joint_count(self) -> int:
+        """Returns the total number of joints in the end effector.
         
+        The joint_names list contains joints for both left and right end effectors.
+        For a single end effector, the number of joints would be joint_names.size/2.
+        
+        Returns:
+            int: The total number of joints in the end effector.
+        """
+        return len(self._joint_names)
+    
     @abstractmethod
     def control(self, target_positions:list, target_velocities:list, target_torques:list)->bool:
         pass
@@ -27,15 +46,15 @@ class EndEffector(ABC):
         pass
 
     @abstractmethod
-    def get_position(self)->Tuple[float, float]:
+    def get_position(self)->Tuple[list, list]:
         pass
 
     @abstractmethod
-    def get_velocity(self)->Tuple[float, float]:
+    def get_velocity(self)->Tuple[list, list]:
         pass
 
     @abstractmethod
-    def get_effort(self)->Tuple[float, float]:
+    def get_effort(self)->Tuple[list, list]:
         pass
 
     @abstractmethod

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/kuavo/__init__.py

@@ -3,5 +3,5 @@ from .robot_info import KuavoRobotInfo
 from .robot_state import KuavoRobotState
 from .robot_arm import KuavoRobotArm
 from .robot_head import KuavoRobotHead
-from .dexterous_hand import DexterousHand
+from .dexterous_hand import DexterousHand, TouchDexterousHand
 from .leju_claw import LejuClaw

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/kuavo/core/core.py

@@ -28,7 +28,7 @@ from transitions import Machine, State
 from kuavo_humanoid_sdk.interfaces.data_types import KuavoArmCtrlMode, KuavoIKParams, KuavoPose
 from kuavo_humanoid_sdk.kuavo.core.ros.control import KuavoRobotControl
 from kuavo_humanoid_sdk.kuavo.core.ros.state import KuavoRobotStateCore
-from kuavo_humanoid_sdk.kuavo.core.ros.param import make_robot_param, kuavo_ros_param
+from kuavo_humanoid_sdk.kuavo.core.ros.param import make_robot_param
 from kuavo_humanoid_sdk.common.logger import SDKLogger
 
 # Define robot states
@@ -78,7 +78,6 @@ class KuavoRobotCore:
          raise RuntimeError if initialize failed.
         """
         try:
-            info = make_robot_param()
             # init state by gait_name
             gait_name = self._rb_state.gait_name()
             if gait_name is not None:
@@ -173,15 +172,20 @@ class KuavoRobotCore:
             SDKLogger.warn(f"[Core] control torso height failed, robot is not in stance state({self.state})!")
             return False
         
-        # Limit height range to [-0.3, 0.0]
-        limited_height = min(0.0, max(-0.3, height))
-        if height > 0.0 or height < -0.3:
-            SDKLogger.warn(f"[Core] height {height} exceeds limit [-0.3, 0.0], will be limited")
+        MIN_HEIGHT = -0.35
+        MAX_HEIGHT = 0.0
+        MIN_PITCH = -0.4
+        MAX_PITCH = 0.4
         
-        # Limit pitch range to [-0.4, 0.4]
-        limited_pitch = min(0.4, max(-0.4, pitch))
-        if abs(pitch) > 0.4:
-            SDKLogger.warn(f"[Core] pitch {pitch} exceeds limit [-0.4, 0.4], will be limited")
+        # Limit height range
+        limited_height = min(MAX_HEIGHT, max(MIN_HEIGHT, height))
+        if height > MAX_HEIGHT or height < MIN_HEIGHT:
+            SDKLogger.warn(f"[Core] height {height} exceeds limit [{MIN_HEIGHT}, {MAX_HEIGHT}], will be limited")
+        
+        # Limit pitch range
+        limited_pitch = min(MAX_PITCH, max(MIN_PITCH, pitch))
+        if abs(pitch) > MAX_PITCH:
+            SDKLogger.warn(f"[Core] pitch {pitch} exceeds limit [{MIN_PITCH}, {MAX_PITCH}], will be limited")
 
         return self._control.control_torso_height(limited_height, limited_pitch)
 
@@ -238,9 +242,9 @@ class KuavoRobotCore:
             max_y_step = 0.20
             max_yaw_step = 90
         else:
-            max_x_step = 0.10
-            max_y_step = 0.10
-            max_yaw_step = 30
+            max_x_step = 0.15
+            max_y_step = 0.15
+            max_yaw_step = 45
         
         body_poses = []
         
@@ -294,6 +298,10 @@ class KuavoRobotCore:
     def control_robot_dexhand(self, left_position:list, right_position:list)->bool:
         return self._control.control_robot_dexhand(left_position, right_position)
     
+    def robot_dexhand_command(self, data, ctrl_mode, hand_side):
+         return self._control.robot_dexhand_command(data, ctrl_mode, hand_side)
+
+
     def control_leju_claw(self, postions:list, velocities:list=[90, 90], torques:list=[1.0, 1.0]) ->bool:
         return self._control.control_leju_claw(postions, velocities, torques)
 

{kuavo_humanoid_sdk-0.1.2 → kuavo_humanoid_sdk-1.1.2a921}/kuavo_humanoid_sdk/kuavo/core/dex_hand_control.py

@@ -4,6 +4,7 @@ from queue import Queue
 from kuavo_humanoid_sdk.interfaces.data_types import EndEffectorSide
 from kuavo_humanoid_sdk.kuavo.core.core import KuavoRobotCore
 from kuavo_humanoid_sdk.common.logger import SDKLogger
+from kuavo_humanoid_sdk.kuavo.core.ros.param import make_robot_param, EndEffectorType
 class DexHandControl:
     _instance = None
 
@@ -19,6 +20,8 @@ class DexHandControl:
             self.thread = threading.Thread(target=self._process_queue)  # Create a thread to process the queue
             self.thread.daemon = True  # Set the thread as a daemon so it will exit when the main program exits
             self.thread.start()  # Start the thread
+            kuavo_info = make_robot_param()
+            self._ee_type = kuavo_info['end_effector_type']
             # Initialize last command position, torque, and velocity
             self.last_cmd_position = {EndEffectorSide.LEFT: [0] * 6, EndEffectorSide.RIGHT: [0] * 6}
             self._initialized = True
@@ -26,6 +29,9 @@ class DexHandControl:
     def control(self, target_positions: list, side: EndEffectorSide):
         self.queue.put(('position', EndEffectorSide(side.value), target_positions))
 
+    def control_velocity(self, target_velocities: list, side: EndEffectorSide):
+        self.queue.put(('velocity', EndEffectorSide(side.value), target_velocities))
+
     def make_gestures(self, gestures:list)->bool:
         """
             Make a gesture for the dexhand.
@@ -60,26 +66,49 @@ class DexHandControl:
             return None
         return gs
     
+    
+    def _process_dexhand_command(self, command, side, data):
+        if command == 'position':
+            pos = self.last_cmd_position[EndEffectorSide.LEFT] + self.last_cmd_position[EndEffectorSide.RIGHT]
+            if side == EndEffectorSide.BOTH:
+                pos = copy.deepcopy(data)
+            elif side == EndEffectorSide.LEFT:
+                pos[:6] = data
+            elif side == EndEffectorSide.RIGHT:
+                pos[6:] = data
+            else:
+                return
+            self._kuavo_core.control_robot_dexhand(left_position=pos[:6], right_position=pos[6:])                       
+            self.last_cmd_position[EndEffectorSide.LEFT] = pos[:6]
+            self.last_cmd_position[EndEffectorSide.RIGHT] = pos[6:]
+
+    def _process_touch_dexhand_command(self, command, side, data):
+        if command == 'position':
+            ctrl_mode = 0
+            if side == EndEffectorSide.BOTH:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 2)
+            elif side == EndEffectorSide.LEFT:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 0)
+            elif side == EndEffectorSide.RIGHT:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 1)
+        elif command == 'velocity':
+            ctrl_mode = 0
+            if side == EndEffectorSide.BOTH:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 2)
+            elif side == EndEffectorSide.LEFT:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 0)
+            elif side == EndEffectorSide.RIGHT:
+                self._kuavo_core.robot_dexhand_command(data, ctrl_mode, 1)
+
     def _process_queue(self):
         while True:
             try:
                 command, side, data = self.queue.get()  # This will block until an item is available in the queue
                 SDKLogger.debug(f'[DexHandControl] Received command: {command}, for side: {side}, with data: {data}')
-                if command == 'position':
-                    pos = self.last_cmd_position[EndEffectorSide.LEFT] + self.last_cmd_position[EndEffectorSide.RIGHT]
-                    if side == EndEffectorSide.BOTH:
-                        pos = copy.deepcopy(data)
-                    elif side == EndEffectorSide.LEFT:
-                        pos[:6] = data
-                    elif side == EndEffectorSide.RIGHT:
-                        pos[6:] = data
-                    else:
-                        return
-                    self._kuavo_core.control_robot_dexhand(left_position=pos[:6], right_position=pos[6:])                       
-                    self.last_cmd_position[EndEffectorSide.LEFT] = pos[:6]
-                    self.last_cmd_position[EndEffectorSide.RIGHT] = pos[6:]
-
-                # task done.
+                if self._ee_type == EndEffectorType.QIANGNAO:
+                    self._process_dexhand_command(command, side, data)
+                elif self._ee_type == EndEffectorType.QIANGNAO_TOUCH:
+                    self._process_touch_dexhand_command(command, side, data)    
                 self.queue.task_done()
             except KeyboardInterrupt:
                 break