User-Driven Learning from Demonstration: A Trajectory and Impedance Learning Method

2026-07-18

AI Summary

This work addresses the limitations of traditional learning-from-demonstration approaches, which rely on repetitive demonstrations and struggle to balance precision with human–robot interaction safety. The authors propose a user-driven, single-demonstration framework that simultaneously learns both motion trajectories and variable impedance parameters from a single demonstration, thereby eliminating the need for repeated teaching while ensuring compliance and contact stability under disturbances. The method integrates 3D fast diffeomorphic matching (FDM), a dynamical systems (DS) motion generator, an extended Kalman filter (EKF), and an impedance parameterization function to enable real-time, high-fidelity compliant motion reproduction. Experimental validation on a 7-DOF KUKA LWR IV+ robot demonstrates the approach’s effectiveness in trajectory reproduction accuracy, real-time impedance adaptation, and recovery from external perturbations.

Abstract

This paper presents a method for user-driven robot Learning from Demonstration (LfD) that reduces user effort while ensuring compliant and precise reproduction. The method eliminates repeated teaching for the same task and enables real-time learning from a single demonstration. Demonstrated motions are reproduced with high precision, while impedance variations are learned in real time to provide both compliance and robustness against perturbations. This mitigates potential safety issues in Human-Robot Interaction (HRI) that arise from conventional time-indexed trajectories lacking compliance. The proposed approach integrates a three-dimensional (3D) Fast Diffeomorphic Matching (FDM) algorithm with a Dynamical System (DS)-based motion generator to achieve real-time single-shot demonstration learning and reproduction. An Extended Kalman Filter (EKF) framework compensates for reproduction errors and recovers from external interactions. Furthermore, an impedance parameterization function is incorporated to learn impedance variations from demonstrations and maintain surface contact for specific applications. The proposed approach is validated through comprehensive experiments on a 7 Degree-of-Freedom (DOF) KUKA LWR IV+ robot.

Problem

• Learning from Demonstration
• Impedance Learning
• Human-Robot Interaction
• Compliant Motion
• Trajectory Reproduction

Innovation

• Learning from Demonstration
• Impedance Learning
• Fast Diffeomorphic Matching
• Dynamical Systems
• Extended Kalman Filter