On the Road to Clarity: Exploring Explainable AI for World Models in a Driver Assistance System

arXiv:2404.17350v1 Announce Type: new
Abstract: In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such as feature relevance estimation and dimensionality reduction. Coarse graining techniques can also help reduce dimensionality and find interpretable global patterns. A specific coarse graining method is Renormalization Groups from statistical physics. It has previously been applied to Restricted Boltzmann …

abstract arxiv autonomous autonomous driving black boxes cs.cv cs.lg cs.ma driver driver assistance system driving explainable ai feature however mistakes networks neural networks safety systems transparency type world world models xai