Explaining Autonomous Vehicles with Intention-aware Policy Graphs
This addresses the need for explainability to improve societal trust and regulatory acceptance of autonomous vehicles, representing an incremental advancement in interpretability methods.
The paper tackles the problem of opaque decision-making in autonomous vehicles by proposing a post-hoc, model-agnostic method using Intention-aware Policy Graphs to generate interpretable explanations for vehicle behavior in urban environments, demonstrated on the nuScenes dataset to assess legal compliance and identify vulnerabilities.
The potential to improve road safety, reduce human driving error, and promote environmental sustainability have enabled the field of autonomous driving to progress rapidly over recent decades. The performance of autonomous vehicles has significantly improved thanks to advancements in Artificial Intelligence, particularly Deep Learning. Nevertheless, the opacity of their decision-making, rooted in the use of accurate yet complex AI models, has created barriers to their societal trust and regulatory acceptance, raising the need for explainability. We propose a post-hoc, model-agnostic solution to provide teleological explanations for the behaviour of an autonomous vehicle in urban environments. Building on Intention-aware Policy Graphs, our approach enables the extraction of interpretable and reliable explanations of vehicle behaviour in the nuScenes dataset from global and local perspectives. We demonstrate the potential of these explanations to assess whether the vehicle operates within acceptable legal boundaries and to identify possible vulnerabilities in autonomous driving datasets and models.