Saved in:
Bibliographic Details
Main Authors: Freitag, Kilian, Combrink, Alvin, Figueroa, Nadia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15445
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912968667561984
author Freitag, Kilian
Combrink, Alvin
Figueroa, Nadia
author_facet Freitag, Kilian
Combrink, Alvin
Figueroa, Nadia
contents Learning motion policies from expert demonstrations is an essential paradigm in modern robotics. While end-to-end models aim for broad generalization, they require large datasets and computationally heavy inference. Conversely, learning dynamical systems (DS) provides fast, reactive, and provably stable control from very few demonstrations. However, existing DS learning methods typically model isolated tasks and struggle to reuse demonstrations for novel behaviors. In this work, we formalize the problem of combining isolated demonstrations within a shared workspace to enable generalization to unseen tasks. The Gaussian Graph is introduced, which reinterprets spatial components of learned motion primitives as discrete vertices with connections to one another. This formulation allows us to bridge continuous control with discrete graph search. We propose two frameworks leveraging this graph: Stitching, for constructing time-invariant DSs, and Chaining, giving a sequence-based DS for complex motions while retaining convergence guarantees. Simulations and real-robot experiments show that these methods successfully generalize to new tasks where baseline methods fail.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15445
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Shot Generalization from Motion Demonstrations to New Tasks
Freitag, Kilian
Combrink, Alvin
Figueroa, Nadia
Robotics
Learning motion policies from expert demonstrations is an essential paradigm in modern robotics. While end-to-end models aim for broad generalization, they require large datasets and computationally heavy inference. Conversely, learning dynamical systems (DS) provides fast, reactive, and provably stable control from very few demonstrations. However, existing DS learning methods typically model isolated tasks and struggle to reuse demonstrations for novel behaviors. In this work, we formalize the problem of combining isolated demonstrations within a shared workspace to enable generalization to unseen tasks. The Gaussian Graph is introduced, which reinterprets spatial components of learned motion primitives as discrete vertices with connections to one another. This formulation allows us to bridge continuous control with discrete graph search. We propose two frameworks leveraging this graph: Stitching, for constructing time-invariant DSs, and Chaining, giving a sequence-based DS for complex motions while retaining convergence guarantees. Simulations and real-robot experiments show that these methods successfully generalize to new tasks where baseline methods fail.
title Zero-Shot Generalization from Motion Demonstrations to New Tasks
topic Robotics
url https://arxiv.org/abs/2603.15445