Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Buriani, Gioele, Liu, Jingyue, Stölzle, Maximilian, Della Santina, Cosimo, Ding, Jiatao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909988155293696
author Buriani, Gioele
Liu, Jingyue
Stölzle, Maximilian
Della Santina, Cosimo
Ding, Jiatao
author_facet Buriani, Gioele
Liu, Jingyue
Stölzle, Maximilian
Della Santina, Cosimo
Ding, Jiatao
contents Reduced-order models are central to motion planning and control of quadruped robots, yet existing templates are often hand-crafted for a specific locomotion modality. This motivates the need for automatic methods that extract task-specific, interpretable low-dimensional dynamics directly from data. We propose a methodology that combines a linear autoencoder with symbolic regression to derive such models. The linear autoencoder provides a consistent latent embedding for configurations, velocities, accelerations, and inputs, enabling the sparse identification of nonlinear dynamics (SINDy) to operate in a compact, physics-aligned space. A multi-phase, hybrid-aware training scheme ensures coherent latent coordinates across contact transitions. We focus our validation on quadruped jumping-a representative, challenging, yet contained scenario in which a principled template model is especially valuable. The resulting symbolic dynamics outperform the state-of-the-art handcrafted actuated spring-loaded inverted pendulum (aSLIP) baseline in simulation and hardware across multiple robots and jumping modalities.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06538
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots
Buriani, Gioele
Liu, Jingyue
Stölzle, Maximilian
Della Santina, Cosimo
Ding, Jiatao
Robotics
Artificial Intelligence
Systems and Control
Reduced-order models are central to motion planning and control of quadruped robots, yet existing templates are often hand-crafted for a specific locomotion modality. This motivates the need for automatic methods that extract task-specific, interpretable low-dimensional dynamics directly from data. We propose a methodology that combines a linear autoencoder with symbolic regression to derive such models. The linear autoencoder provides a consistent latent embedding for configurations, velocities, accelerations, and inputs, enabling the sparse identification of nonlinear dynamics (SINDy) to operate in a compact, physics-aligned space. A multi-phase, hybrid-aware training scheme ensures coherent latent coordinates across contact transitions. We focus our validation on quadruped jumping-a representative, challenging, yet contained scenario in which a principled template model is especially valuable. The resulting symbolic dynamics outperform the state-of-the-art handcrafted actuated spring-loaded inverted pendulum (aSLIP) baseline in simulation and hardware across multiple robots and jumping modalities.
title Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots
topic Robotics
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2508.06538