Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation
This addresses unpredictable errors in robotic manipulation for scenarios involving confusable objects, representing an incremental improvement.
The paper tackles the lack of robustness in vision-language models for robotic manipulation, particularly in scenarios with confusable objects, by proposing Confusion-Aware In-Context Learning, which achieves an 85.5% success rate on VIMA-Bench.
Vision-language models (VLMs) have significantly improved the generalization capabilities of robotic manipulation. However, VLM-based systems often suffer from a lack of robustness, leading to unpredictable errors, particularly in scenarios involving confusable objects. Our preliminary analysis reveals that these failures are mainly caused by shortcut learning problem inherently in VLMs, limiting their ability to accurately distinguish between confusable features. To this end, we propose Confusion-Aware In-Context Learning (CAICL), a method that enhances VLM performance in confusable scenarios for robotic manipulation. The approach begins with confusion localization and analysis, identifying potential sources of confusion. This information is then used as a prompt for the VLM to focus on features most likely to cause misidentification. Extensive experiments on the VIMA-Bench show that CAICL effectively addresses the shortcut learning issue, achieving a 85.5\% success rate and showing good stability across tasks with different degrees of generalization.