Paper ID: 2409.12894

Towards Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation: An Empirical Study

Zhijie Wang, Zhehua Zhou, Jiayang Song, Yuheng Huang, Zhan Shu, Lei Ma

Multi-modal foundation models and generative AI have demonstrated promising capabilities in applications across various domains. Recently, Vision-language-action (VLA) models have attracted much attention regarding their potential to advance robotic manipulation. Despite the end-to-end perception-control loop offered by the VLA models, there is a lack of comprehensive understanding of the capabilities of such models and an automated testing platform to reveal their robustness and reliability across different robotic manipulation scenarios. To address these challenges, in this work, we present VLATest, a testing framework that automatically generates diverse robotic manipulation scenes to assess the performance of VLA models from various perspectives. Large-scale experiments are considered, including eight VLA models, four types of manipulation tasks, and over 18,604 testing scenes. The experimental results show that existing VAL models still lack imperative robustness for practical applications. Specifically, the performance of VLA models can be significantly affected by several factors from the operation environments, such as camera poses, lighting conditions, and unseen objects. Our framework and the insights derived from the study are expected to pave the way for more advanced and reliable VLA-enabled robotic manipulation systems in practice.

Submitted: Sep 19, 2024