LATIDIA · Robótica

Pruebas de robustez generalizables de sistemas de navegación robóticos basados en DNN a través de búsqueda guiada por XAI

arXiv: 2610.06862v1Tipo de anuncio: nuevo Resumen: * * Contexto: * * Las redes neuronales profundas (DNN) controlan cada vez más los sistemas ciberfísicos (CPS), pero las pequeñas perturbaciones de entrada pueden causar un comportamiento inseguro a nivel del sistema.

La noticia

arXiv:2610.06862v1 Announce Type: new Abstract: **Context:** Deep Neural Networks (DNNs) increasingly control Cyber-Physical Systems (CPSs), yet small input perturbations can cause unsafe system-level behavior. Existing approaches often optimize perturbations for individual images and evaluate them only in simulation, limiting their generalizability and practical validity. **Objectives:** This work aims to generate robustness tests that remain effective across operational observations and to evaluate whether the resulting failures transfer from simulation to a physical robot. **Methods:** We propose an explainability-guided multi-objective evolutionary approach that generates sparse perturbations over representative images selected through visual and behavioral clustering. Aggregated Integrated Gradients guide mutations toward influential image regions. We evaluate the approach on a DNN-controlled LeoRover