RoboTwin-Phys: Do WAMs and VLAs Understand the Physical World?

2026-09-22

AI Summary

针对机器人操作中物理条件多样性不足的问题，通过引入RoboTwin-Phys基准，连续变化13个物理属性来评估模型在不同物理条件下的鲁棒性。

Abstract

Physical-condition diversity is largely missing from current benchmarks for robot manipulation. While large-scale simulation benchmarks increasingly incorporate variations in object appearance, scene layout, and visual observations, they typically keep the underlying physical parameters fixed. As a result, important sources of real-world variability, such as changes in mass, friction, and joint dynamics, remain largely untested. We introduce RoboTwin-Phys, a physics-diverse benchmark that treats physical-condition diversity as an explicit dimension of robot manipulation evaluation. The benchmark continuously varies 13 physical attributes within physically plausible ranges, providing a unified setting for evaluating policies across diverse physical operating conditions. We further release more than 5,000 expert demonstrations with ground-truth physical parameters, enabling physical-attribute estimation, condition-aware modeling, and physics-conditioned policy training. Evaluations of representative WAMs and VLAs reveal a substantial robustness gap: models that remain effective under existing visual and layout randomization can degrade markedly under changes in physical conditions. RoboTwin-Phys provides the benchmark, data, and evaluation protocol needed to systematically measure and improve robustness to physical-condition diversity in robot manipulation.

Problem

• Physical-condition diversity
• Robot manipulation
• Benchmark
• Simulation
• Real-world variability

Innovation

• physics-diverse benchmark
• physical-condition diversity
• robot manipulation
• condition-aware modeling
• physics-conditioned policy training