ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation

2026-09-20

AI Summary

为解决模拟与现实性能差异问题，提出ReVeal框架，通过重建环境、评估重建水平及匹配闭环策略评估，提高VLA政策评估准确性。

Abstract

Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, reconstruction errors can cause simulated policy performance to diverge from real-world performance, motivating the need to assess reconstructed environments for downstream VLA policy evaluation. We present ReVeal, a real-to-sim assessment framework combining workspace reconstruction, reconstruction-level assessment, and matched closed-loop policy evaluation. Novel-View Mesh Fidelity (NVMF) and Annotated Planar Geometry Fidelity (APGF) assess observation and planar geometric fidelity, respectively. We also develop PGSR-D, a reconstruction pipeline incorporating monocular depth supervision to improve geometry where multi-view visual cues are limited. Across 8 assessment scenes, NVMF and APGF consistently distinguish the fidelity of 2DGS, PGSR, and PGSR-D. Matched evaluations of GR00T, SmolVLA, and pi0.5 across 8 humanoid manipulation tasks show consistent ordering between reconstruction fidelity and real-sim performance agreement across pipelines. Further analysis of the evaluation workspaces shows that higher fidelity is associated with stronger real-sim agreement.

Problem

• Simulation-based Evaluation
• Reconstruction Errors
• Vision-Language-Action Policies
• Fidelity Assessment
• Real-to-Sim

Innovation

• Reconstruction-Aware
• Novel-View Mesh Fidelity (NVMF)
• Annotated Planar Geometry Fidelity (APGF)
• PGSR-D