Consensus-based optimization (CBO): Towards Global Optimality in Robotics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Xudong, Jordana, Armand, Fornasier, Massimo, Etesami, Jalal, Khadiv, Majid
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912884961837056
author Sun, Xudong
Jordana, Armand
Fornasier, Massimo
Etesami, Jalal
Khadiv, Majid
author_facet Sun, Xudong
Jordana, Armand
Fornasier, Massimo
Etesami, Jalal
Khadiv, Majid
contents Zero-order optimization has recently received significant attention for designing optimal trajectories and policies for robotic systems. However, most existing methods (e.g., MPPI, CEM, and CMA-ES) are local in nature, as they rely on gradient estimation. In this paper, we introduce consensus-based optimization (CBO) to robotics, which is guaranteed to converge to a global optimum under mild assumptions. We provide theoretical analysis and illustrative examples that give intuition into the fundamental differences between CBO and existing methods. To demonstrate the scalability of CBO for robotics problems, we consider three challenging trajectory optimization scenarios: (1) a long-horizon problem for a simple system, (2) a dynamic balance problem for a highly underactuated system, and (3) a high-dimensional problem with only a terminal cost. Our results show that CBO is able to achieve lower costs with respect to existing methods on all three challenging settings. This opens a new framework to study global trajectory optimization in robotics.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06868
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Consensus-based optimization (CBO): Towards Global Optimality in Robotics
Sun, Xudong
Jordana, Armand
Fornasier, Massimo
Etesami, Jalal
Khadiv, Majid
Robotics
Zero-order optimization has recently received significant attention for designing optimal trajectories and policies for robotic systems. However, most existing methods (e.g., MPPI, CEM, and CMA-ES) are local in nature, as they rely on gradient estimation. In this paper, we introduce consensus-based optimization (CBO) to robotics, which is guaranteed to converge to a global optimum under mild assumptions. We provide theoretical analysis and illustrative examples that give intuition into the fundamental differences between CBO and existing methods. To demonstrate the scalability of CBO for robotics problems, we consider three challenging trajectory optimization scenarios: (1) a long-horizon problem for a simple system, (2) a dynamic balance problem for a highly underactuated system, and (3) a high-dimensional problem with only a terminal cost. Our results show that CBO is able to achieve lower costs with respect to existing methods on all three challenging settings. This opens a new framework to study global trajectory optimization in robotics.
title Consensus-based optimization (CBO): Towards Global Optimality in Robotics
topic Robotics
url https://arxiv.org/abs/2602.06868