Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cuellar, Alex, Fourie, Christopher K, Shah, Julie A
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.14988
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915626625269760
author Cuellar, Alex
Fourie, Christopher K
Shah, Julie A
author_facet Cuellar, Alex
Fourie, Christopher K
Shah, Julie A
contents Learning from Demonstration (LfD) has shown to provide robots with fundamental motion skills for a variety of domains. Various branches of LfD research (e.g., learned dynamical systems and movement primitives) can generally be classified into ''time-dependent'' or ''time-independent'' systems. Each provides fundamental benefits and drawbacks -- time-independent methods cannot learn overlapping trajectories, while time-dependence can result in undesirable behavior under perturbation. This paper introduces Cluster Alignment for Learned Motions (CALM), an LfD framework dependent upon an alignment with a representative ''mean" trajectory of demonstrated motions rather than pure time- or state-dependence. We discuss the convergence properties of CALM, introduce an alignment technique able to handle the shifts in alignment possible under perturbation, and utilize demonstration clustering to generate multi-modal behavior. We show how CALM mitigates the drawbacks of time-dependent and time-independent techniques on 2D datasets and implement our system on a 7-DoF robot learning tasks in three domains.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14988
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Alignment-Based Approach to Learning Motions from Demonstrations
Cuellar, Alex
Fourie, Christopher K
Shah, Julie A
Robotics
Learning from Demonstration (LfD) has shown to provide robots with fundamental motion skills for a variety of domains. Various branches of LfD research (e.g., learned dynamical systems and movement primitives) can generally be classified into ''time-dependent'' or ''time-independent'' systems. Each provides fundamental benefits and drawbacks -- time-independent methods cannot learn overlapping trajectories, while time-dependence can result in undesirable behavior under perturbation. This paper introduces Cluster Alignment for Learned Motions (CALM), an LfD framework dependent upon an alignment with a representative ''mean" trajectory of demonstrated motions rather than pure time- or state-dependence. We discuss the convergence properties of CALM, introduce an alignment technique able to handle the shifts in alignment possible under perturbation, and utilize demonstration clustering to generate multi-modal behavior. We show how CALM mitigates the drawbacks of time-dependent and time-independent techniques on 2D datasets and implement our system on a 7-DoF robot learning tasks in three domains.
title An Alignment-Based Approach to Learning Motions from Demonstrations
topic Robotics
url https://arxiv.org/abs/2511.14988