Arc-Length-Based Warping for Robot Skill Synthesis from Multiple Demonstrations

TL;DR

This paper introduces an arc-length-based warping method for robot skill learning from multiple demonstrations, removing the need for temporal alignment and improving robustness in variable-speed, intermittent movements.

Contribution

The novel Spatial Sampling algorithm enables time-independent trajectory alignment using arc-length parametrization, enhancing skill extraction accuracy in kinesthetic teaching scenarios.

Findings

Outperforms state-of-the-art algorithms in trajectory synchronization

Achieves higher quality of skill extraction from variable-speed demonstrations

Demonstrates robustness in intermittent and irregular movements

Abstract

In robotics, Learning from Demonstration (LfD) aims to transfer skills to robots by using multiple demonstrations of the same task. These demonstrations are recorded and processed to extract a consistent skill representation. This process typically requires temporal alignment through techniques such as Dynamic Time Warping (DTW). In this paper, we consider a novel algorithm, named Spatial Sampling (SS), specifically designed for robot trajectories, that enables time-independent alignment of the trajectories by providing an arc-length parametrization of the signals. This approach eliminates the need for temporal alignment, enhancing the accuracy and robustness of skill representation, especially when recorded movements are subject to intermittent motions or extremely variable speeds, a common characteristic of operations based on kinesthetic teaching, where the operator may encounter difficulties in guiding the end-effector smoothly. To prove this, we built a custom publicly available dataset of robot recordings to test real-world movements, where the user tracks the same geometric path multiple times, with motion laws that vary greatly and are subject to starting and stopping. The SS demonstrates better performances against state-of-the-art algorithms in terms of (i) trajectory synchronization and (ii) quality of the extracted skill.