Related Experiment Video
Updated: Aug 8, 2026

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
Published on: May 8, 2021
Temporal compensation physics-informed neural network modeling repetitive small-range rotation inverse dynamics
Fangyu Li1, Man Li1, Honggui Han1
1School of Information Science and Technology, Beijing University of Technology, Beijing, 100124, China; Engineering Research Center of Digital Community Ministry of Education, Beijing University of Technology, Beijing, 100124, China.
This study introduces a temporal compensation physics-informed neural network (TC-PINN) to address dynamic hysteresis in robotic motion mapping. The novel TC-PINN model significantly enhances accuracy for high-precision robotic operations.
Area of Science:
- Robotics
- Control Systems
- Machine Learning
Background:
- High-fidelity motion mapping is crucial for precise robotic tasks.
- Existing models struggle with dynamic hysteresis during small-range rotations, reducing accuracy.
Purpose of the Study:
- To develop a novel method for mitigating dynamic hysteresis effects in robotic motion mapping.
- To improve the accuracy of torque mapping in robotic arms.
Main Methods:
- A temporal compensation physics-informed neural network (TC-PINN) was proposed.
- A rotational state trajectory with cumulative joint rotation features was constructed.
- A Linformer-based nonlinear error fitting structure was designed for compensation.
Main Results:
- TC-PINN effectively mitigates dynamic hysteresis effects.
- Hysteresis-aware torque mapping accuracy was improved on a 7-DOF robotic arm.
- The total mean absolute error was reduced to 9.65×10-4 Nm.
Conclusions:
- The proposed TC-PINN offers a viable solution for enhancing robotic motion mapping accuracy.
- This approach is particularly effective for repetitive small-range rotations with hysteresis.
- The method contributes to more reliable and precise robotic operations.
Related Concept Videos
Kinematic Equations for Rotation
For instance, imagine a point A on a rigid body engaged in circular motion. The translational velocity of this particular point can be calculated by taking the time derivatives of the displacement equation, which essentially measures the...
Linear Approximation in Time Domain
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length, the...
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
Relative Motion Analysis using Rotating Axes
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it instrumental in...
Rotation with Constant Angular Acceleration - I
Using our intuition, we can begin to see how rotational quantities such as angular displacement, angular velocity, angular acceleration, and time are related to one another. For example, if a flywheel...
Rotation with Constant Angular Acceleration - II
The first...