LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yoon, Jihwan, Jeong, Taemoon, Park, Jeongeun, Kim, Chanwoo, Kwon, Jaewoon, Lee, Yonghyeon, Lee, Kyungjae, Choi, Sungjoon
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917398925279232
author Yoon, Jihwan
Jeong, Taemoon
Park, Jeongeun
Kim, Chanwoo
Kwon, Jaewoon
Lee, Yonghyeon
Lee, Kyungjae
Choi, Sungjoon
author_facet Yoon, Jihwan
Jeong, Taemoon
Park, Jeongeun
Kim, Chanwoo
Kwon, Jaewoon
Lee, Yonghyeon
Lee, Kyungjae
Choi, Sungjoon
contents Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimization offers a promising path toward automation, but two major challenges remain: (i) the vast, unstructured design space and (ii) the difficulty of constructing task-specific loss functions. We propose a new paradigm that minimizes human involvement by (i) learning the design search space from existing mechanical designs, rather than hand-crafting it, and (ii) defining the loss directly from human motion data via motion retargeting and Procrustes analysis. Using screw-theory-based joint axis representation and isometric manifold learning, we construct a compact, geometry-preserving latent space of humanoid upper body designs in which optimization is tractable. We then solve design optimization in this latent space using gradient-free optimization. Our approach establishes a principled framework for data-driven robot design and demonstrates that leveraging existing designs and human motion can effectively guide the automated discovery of novel robot design.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08636
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design
Yoon, Jihwan
Jeong, Taemoon
Park, Jeongeun
Kim, Chanwoo
Kwon, Jaewoon
Lee, Yonghyeon
Lee, Kyungjae
Choi, Sungjoon
Robotics
Artificial Intelligence
Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimization offers a promising path toward automation, but two major challenges remain: (i) the vast, unstructured design space and (ii) the difficulty of constructing task-specific loss functions. We propose a new paradigm that minimizes human involvement by (i) learning the design search space from existing mechanical designs, rather than hand-crafting it, and (ii) defining the loss directly from human motion data via motion retargeting and Procrustes analysis. Using screw-theory-based joint axis representation and isometric manifold learning, we construct a compact, geometry-preserving latent space of humanoid upper body designs in which optimization is tractable. We then solve design optimization in this latent space using gradient-free optimization. Our approach establishes a principled framework for data-driven robot design and demonstrates that leveraging existing designs and human motion can effectively guide the automated discovery of novel robot design.
title LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2604.08636