RoboFAC: A
Comprehensive Framework for Robotic Failure
Analysis and Correction
Overview of our RoboFAC framework.
Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and image information into sequential control actions. However, these models often underperform in open-world scenarios, as they are predominantly trained on successful expert demonstrations and exhibit a limited capacity for failure recovery. In this work, we present a Robotic Failure Analysis and Correction (RoboFAC) framework to address this issue. Firstly, we construct RoboFAC dataset comprising 9,440 erroneous manipulation trajectories and 78,623 QA pairs across 16 diverse tasks and 53 scenes in both simulation and real-world environments. Leveraging our dataset, we develop RoboFAC model, which is capable of Task Understanding, Failure Analysis and Failure Correction. Experimental results demonstrate that the RoboFAC model outperforms GPT-4o by 34.1% on our evaluation benchmark. Furthermore, we integrate the RoboFAC model into a real-world VLA control pipeline as an external supervision providing correction instructions, yielding a 29.1% relative improvement on average on four real-world tasks. The results show that our RoboFAC framework effectively handles robotic failures and assists the VLA model in recovering from failures.
Overview of our RoboFAC framework.
Overview of RoboFAC dataset.
Statistics of the RoboFAC Dataset.
Scores for different dimensions on RoboFAC Benchmark.
Success rate on real-world manipulation.
Demo of failure correction in real-world tasks.
@misc{lu2025robofaccomprehensiveframeworkrobotic,
title={RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction},
author={Weifeng Lu and Minghao Ye and Zewei Ye and Ruihan Tao and Shuo Yang and Bo Zhao},
year={2025},
eprint={2505.12224},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2505.12224},
}