Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Xuning, Eppner, Clemens, Tremblay, Jonathan, Fox, Dieter, Birchfield, Stan, Ramos, Fabio
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916901212389376
author Yang, Xuning
Eppner, Clemens
Tremblay, Jonathan
Fox, Dieter
Birchfield, Stan
Ramos, Fabio
author_facet Yang, Xuning
Eppner, Clemens
Tremblay, Jonathan
Fox, Dieter
Birchfield, Stan
Ramos, Fabio
contents Current vision-based robotics simulation benchmarks have significantly advanced robotic manipulation research. However, robotics is fundamentally a real-world problem, and evaluation for real-world applications has lagged behind in evaluating generalist policies. In this paper, we discuss challenges and desiderata in designing benchmarks for generalist robotic manipulation policies for the goal of sim-to-real policy transfer. We propose 1) utilizing high visual-fidelity simulation for improved sim-to-real transfer, 2) evaluating policies by systematically increasing task complexity and scenario perturbation to assess robustness, and 3) quantifying performance alignment between real-world performance and its simulation counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective
Yang, Xuning
Eppner, Clemens
Tremblay, Jonathan
Fox, Dieter
Birchfield, Stan
Ramos, Fabio
Robotics
Current vision-based robotics simulation benchmarks have significantly advanced robotic manipulation research. However, robotics is fundamentally a real-world problem, and evaluation for real-world applications has lagged behind in evaluating generalist policies. In this paper, we discuss challenges and desiderata in designing benchmarks for generalist robotic manipulation policies for the goal of sim-to-real policy transfer. We propose 1) utilizing high visual-fidelity simulation for improved sim-to-real transfer, 2) evaluating policies by systematically increasing task complexity and scenario perturbation to assess robustness, and 3) quantifying performance alignment between real-world performance and its simulation counterparts.
title Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective
topic Robotics
url https://arxiv.org/abs/2508.11117