Biped robot form optimization method based on metric index identification variable additive grouping

By identifying additive grouping structures using metrics and employing the K-Means clustering algorithm, the problem of unstable grouping in bipedal robot morphology optimization was solved, achieving efficient and reliable optimization results.

CN122153654APending Publication Date: 2026-06-05NANJING UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202610359421.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-23
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing Bayesian optimization methods based on additive grouping structures are inaccurate and inefficient in bipedal robot morphology optimization, especially under limited evaluation budgets, where grouping evaluation bias and joint sampling complexity are high, leading to unstable optimization results.

Method used

An additive grouping structure identification method based on metrics is adopted. By calculating the interaction strength of variables and converting it into a distance matrix, the K-Means clustering algorithm with capacity constraints is used to group the variables and construct an additive kernel GP surrogate model to obtain the next evaluation point.

Benefits of technology

Stable additive grouping of identification variables under limited samples improves the fitting efficiency of surrogate models, achieves high efficiency and reliability in bipedal robot morphology optimization, and simplifies the optimization process.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a biped robot form optimization method based on metric index identification variable additive grouping. The method comprises an additive structure grouping stage and a Bayesian optimization stage based on additive decomposition. In the additive structure grouping stage, firstly, the interaction strength between every two variables is calculated through a designed inter-variable interaction measurement index, and the interaction strength is converted into a distance matrix; then, the distance matrix is used, a K-Means clustering algorithm with capacity limitation is adopted to cluster the high-dimensional variables to obtain groups, and therefore an additive grouping structure is obtained; and in a Bayesian optimization stage based on additive decomposition, constructing an additive kernel GP agent model by using the obtained additive grouping structure, obtaining a next evaluation point by maximizing an obtaining function, and taking morphological parameters of the evaluation point as initial morphological parameters of the finally applied biped robot. Compared with an existing method, the method is simpler and more stable, and the optimization efficiency and the grouping recognition precision are balanced by limiting the maximum dimension of each subgroup.
Need to check novelty before this filing date? Find Prior Art