An Integrated Compensation Method for the Force Disturbance of a Six-Axis Force Sensor in Complex Manufacturing...

Area of Science:

• Robotics
• Sensor Technology
• Machine Learning

Background:

• Six-axis force sensors are crucial for robot compliance control and human-robot interaction.
• Sensor data is often distorted by zero drift, system errors, and robot end-effector gravity.
• Accurate force sensing is vital for complex manufacturing tasks.

Purpose of the Study:

• To develop an integrated compensation method for six-axis force sensors.
• To eliminate disturbances caused by sensor drift, system errors, and gravity.
• To improve the accuracy and robustness of force measurements in robotic applications.

Main Methods:

• Utilized a deep learning network for zero-point prediction.
• Employed the least squares method for tool load identification.
• Integrated these techniques for automatic compensation of force sensor data.

Main Results:

• The proposed method effectively compensates for force disturbances.
• Experimental results demonstrate high measurement accuracy.
• The compensation is robust in complex manufacturing scenarios.

Conclusions:

• The integrated compensation method significantly enhances six-axis force sensor performance.
• This approach enables more reliable active compliance control and human-robot collaboration.
• The study validates the effectiveness of deep learning and least squares for sensor error correction.