Explainable Adversarial-Robust Vision-Language-Action Model for Robotic Manipulation

TL;DR

This paper introduces an explainable, adversarial-robust vision-language-action model for robotic manipulation in smart farming, enhancing resilience and interpretability against photometric perturbations.

Contribution

The paper presents a novel model integrating an Evidence-3 module for detecting perturbations and providing natural language explanations, improving robustness and explainability in robotic manipulation.

Findings

Reduces Current Action L1 loss by 21.7%

Reduces Next Actions L1 loss by 18.4%

Improves action prediction accuracy under adversarial conditions

Abstract

Smart farming has emerged as a key technology for advancing modern agriculture through automation and intelligent control. However, systems relying on RGB cameras for perception and robotic manipulators for control, common in smart farming, are vulnerable to photometric perturbations such as hue, illumination, and noise changes, which can cause malfunction under adversarial attacks. To address this issue, we propose an explainable adversarial-robust Vision-Language-Action model based on the OpenVLA-OFT framework. The model integrates an Evidence-3 module that detects photometric perturbations and generates natural language explanations of their causes and effects. Experiments show that the proposed model reduces Current Action L1 loss by 21.7% and Next Actions L1 loss by 18.4% compared to the baseline, demonstrating improved action prediction accuracy and explainability under adversarial conditions.