Robotic Calibration Based on Haptic Feedback Improves Sim-to-Real Transfer

TL;DR

This paper introduces a haptic feedback calibration method for robotic arms that improves the accuracy of sim-to-real transfer by reducing end effector positioning errors using neural networks.

Contribution

A novel calibration approach utilizing haptic feedback and neural networks to align simulated and real robot end effector positions.

Findings

Neural network models outperform linear transformations in calibration accuracy.

Significant reduction in end effector positioning errors achieved.

Method enhances the reliability of sim-to-real transfer in robotic manipulation.

Abstract

When inverse kinematics (IK) is adopted to control robotic arms in manipulation tasks, there is often a discrepancy between the end effector (EE) position of the robot model in the simulator and the physical EE in reality. In most robotic scenarios with sim-to-real transfer, we have information about joint positions in both simulation and reality, but the EE position is only available in simulation. We developed a novel method to overcome this difficulty based on haptic feedback calibration, using a touchscreen in front of the robot that provides information on the EE position in the real environment. During the calibration procedure, the robot touches specific points on the screen, and the information is stored. In the next stage, we build a transformation function from the data based on linear transformation and neural networks that is capable of outputting all missing variables from any partial input (simulated/real joint/EE position). Our results demonstrate that a fully nonlinear neural network model performs best, significantly reducing positioning errors.