Parameter-Free Segmentation of Robot Movements with Cross-Correlation Using Different Similarity Metrics

2025-05-09

AI Summary

Existing robot motion demonstration segmentation methods rely heavily on manual parameter tuning and lack adaptability in extracting fundamental motion primitives. Method: This paper proposes a fully parameter-free automatic segmentation framework. Its core innovation lies in the first integration of an enhanced cross-correlation signal processing framework with multiple robot-motion-aware similarity metrics—dynamic time warping, Euclidean distance, and phase correlation—enabling end-to-end, parameterless decomposition of complex demonstration sequences. The method requires no prior knowledge or hyperparameter adjustment and ensures both real-time performance and robustness. Results: Experiments on both simulation and real robotic platforms demonstrate significantly higher segmentation accuracy compared to state-of-the-art parametric and non-parametric baselines. The approach establishes a novel, interpretable, and reusable paradigm for action unitization in robot skill learning.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Often, robots are asked to execute primitive movements, whether as a single action or in a series of actions representing a larger, more complex task. These movements can be learned in many ways, but a common one is from demonstrations presented to the robot by a teacher. However, these demonstrations are not always simple movements themselves, and complex demonstrations must be broken down, or segmented, into primitive movements. In this work, we present a parameter-free approach to segmentation using techniques inspired by autocorrelation and cross-correlation from signal processing. In cross-correlation, a representative signal is found in some larger, more complex signal by correlating the representative signal with the larger signal. This same idea can be applied to segmenting robot motion and demonstrations, provided with a representative motion primitive. This results in a fast and accurate segmentation, which does not take any parameters. One of the main contributions of this paper is the modification of the cross-correlation process by employing similarity metrics that can capture features specific to robot movements. To validate our framework, we conduct several experiments of complex tasks both in simulation and in real-world. We also evaluate the effectiveness of our segmentation framework by comparing various similarity metrics.

Problem

• Segmenting robot movements without parameters using cross-correlation
• Comparing similarity metrics for robot motion segmentation
• Validating segmentation accuracy in simulation and real-world tasks

Innovation

• Parameter-free segmentation using cross-correlation
• Modified cross-correlation with robot-specific similarity metrics
• Fast, accurate segmentation without tuning parameters