Divide et Impera: Decoding Impedance Strategies for Robotic Peg-in-Hole Assembly

2024-10-01

AI Summary

This work addresses the challenge of experience-dependent, non-generalizable impedance parameter tuning in robotic peg-in-hole assembly. We propose a task-oriented impedance strategy analysis and prediction framework. Leveraging the Elementary Dynamic Actions (EDA) formalism, we perform clustering and principal component analysis on multiple sets of successful impedance parameters, revealing—for the first time—an impedance pattern that simultaneously exhibits task specificity and cross-workpiece generalizability. Subsequently, we design a lightweight neural network predictor that enables end-to-end mapping from task-level features to optimal impedance parameters. The method is validated on real-robot experiments involving four geometrically distinct pegs, demonstrating significant reduction in deployment barriers for non-expert users. To foster reproducibility and accessibility in contact-rich manipulation, we publicly release our source code, CAD models, and pre-trained models.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This paper investigates robotic peg-in-hole assembly using the Elementary Dynamic Actions (EDA) framework, which models contact-rich tasks through a combination of submovements, oscillations, and mechanical impedance. Rather than focusing on a single optimal parameter set, we analyze the distribution and structure of multiple successful impedance solutions, revealing patterns that guide impedance selection in contactrich robotic manipulation. Experiments with a real robot and four different peg types demonstrate the presence of task-specific and generalized assembly strategies, identified through K-means Clustering. Principal Component Analysis (PCA) is used to represent these findings, highlighting patterns in successful impedance selections. Additionally, a neural-network-based success predictor accurately estimates feasible impedance parameters, reducing the need for extensive trial-and-error tuning. By providing publicly available code, CAD files, and a trained model, this work enhances the accessibility of impedance control and offers a structured approach to programming robotic assembly tasks, particularly for less-experienced users.

Problem

• Analyzes multiple impedance solutions for robotic peg-in-hole assembly.
• Identifies task-specific and generalized assembly strategies using clustering.
• Develops a neural network to predict feasible impedance parameters.

Innovation

• Elementary Dynamic Actions framework for contact-rich tasks
• K-means Clustering identifies task-specific assembly strategies
• Neural-network predicts feasible impedance parameters accurately