Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
This work addresses a critical safety issue for robotic systems in indoor environments, though it is incremental in nature.
The study tackled the vulnerability of indoor robotic navigation systems to adversarial attacks by reinforcing adversarial training with a novel distance loss function, achieving satisfactory robustness improvements.
Endeavors in indoor robotic navigation rely on the accuracy of segmentation models to identify free space in RGB images. However, deep learning models are vulnerable to adversarial attacks, posing a significant challenge to their real-world deployment. In this study, we identify vulnerabilities within the hidden layers of neural networks and introduce a practical approach to reinforce traditional adversarial training. Our method incorporates a novel distance loss function, minimizing the gap between hidden layers in clean and adversarial images. Experiments demonstrate satisfactory performance in improving the model's robustness against adversarial perturbations.