Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencoder

Autonomous driving presents a complex challenge, which is usually addressed with artificial intelligence models that are end-to-end or modular in nature. Within the landscape of modular approaches, a bio-inspired neural circuit policy model has emerged as an innovative control module, offering a compact and inherently interpretable system to infer a steering wheel command from abstract visual features. Here, we take a leap forward by integrating a variational autoencoder with the neural circuit policy controller, forming a solution that directly generates steering commands from input camera images. By substituting the traditional convolutional neural network approach to feature extraction with a variational autoencoder, we enhance the system’s interpretability, enabling a more transparent and understandable decision- making process. In addition to the architectural shift toward a vari- ational autoencoder, this study introduces the auto- matic latent perturbation tool, a novel contribution designed to probe and elucidate the latent features within the variational autoencoder. The automatic la- tent perturbation tool automates the interpretability process, offering granular insights into how specific latent variables influence the overall model’s behav- ior. Through a series of numerical experiments, we demonstrate the interpretative power of the varia- tional autoencoder-neural circuit policy model and the utility of the automatic latent perturbation tool in making the inner workings of autonomous driving systems more transparent.