Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pacelli, Vincent, Ratheesh, Akash, Theodorou, Evangelos A.
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.02147
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914527545655296
author Pacelli, Vincent
Ratheesh, Akash
Theodorou, Evangelos A.
author_facet Pacelli, Vincent
Ratheesh, Akash
Theodorou, Evangelos A.
contents Sampling-based model predictive control methods like MPPI and CEM are essential for real-time control of nonlinear robotic systems, particularly where discontinuous dynamics preclude gradient-based optimization. However, these methods derive from information-theoretic objectives that are agnostic to the geometry of the control problem, leading to pathological behaviors such as mode-averaging when the cost landscape is complex. We present OT-MPC, a sampling-based algorithm that overcomes these limitations through an entropy-regularized optimal transport formulation. By computing an optimal coupling between candidate control sequences and low-cost proposals, OT-MPC refines candidates toward nearby promising samples while coordinating updates across the ensemble to maintain coverage of the solution space. We derive closed-form, gradient-free updates via the Sinkhorn algorithm, enabling real-time performance. Experiments on navigation, manipulation, and locomotion tasks demonstrate improved success rates over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02147
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sampling-Based Control via Entropy-Regularized Optimal Transport
Pacelli, Vincent
Ratheesh, Akash
Theodorou, Evangelos A.
Robotics
Optimization and Control
Sampling-based model predictive control methods like MPPI and CEM are essential for real-time control of nonlinear robotic systems, particularly where discontinuous dynamics preclude gradient-based optimization. However, these methods derive from information-theoretic objectives that are agnostic to the geometry of the control problem, leading to pathological behaviors such as mode-averaging when the cost landscape is complex. We present OT-MPC, a sampling-based algorithm that overcomes these limitations through an entropy-regularized optimal transport formulation. By computing an optimal coupling between candidate control sequences and low-cost proposals, OT-MPC refines candidates toward nearby promising samples while coordinating updates across the ensemble to maintain coverage of the solution space. We derive closed-form, gradient-free updates via the Sinkhorn algorithm, enabling real-time performance. Experiments on navigation, manipulation, and locomotion tasks demonstrate improved success rates over existing methods.
title Sampling-Based Control via Entropy-Regularized Optimal Transport
topic Robotics
Optimization and Control
url https://arxiv.org/abs/2605.02147