Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction

TL;DR

This paper presents a neuro-symbolic approach combining deep learning and fuzzy logic to enhance explainability and interpretability in pedestrian crossing prediction for autonomous driving, evaluated on PIE and JAAD datasets.

Contribution

A novel neuro-symbolic model (ExPedCross) that integrates explainable features and fuzzy inference for transparent pedestrian crossing predictions.

Findings

Achieved explainability and interpretability in pedestrian crossing prediction.

Provided guidelines for dataset and feature selection to improve explainability.

Demonstrated effectiveness on PIE and JAAD datasets.

Abstract

In the context of autonomous driving, pedestrian crossing prediction is a key component for improving road safety. Presently, the focus of these predictions extends beyond achieving trustworthy results; it is shifting towards the explainability and interpretability of these predictions. This research introduces a novel neuro-symbolic approach that combines deep learning and fuzzy logic for an explainable and interpretable pedestrian crossing prediction. We have developed an explainable predictor (ExPedCross), which utilizes a set of explainable features and employs a fuzzy inference system to predict whether the pedestrian will cross or not. Our approach was evaluated on both the PIE and JAAD datasets. The results offer experimental insights into achieving explainability and interpretability in the pedestrian crossing prediction task. Furthermore, the testing results yield a set of guidelines and recommendations regarding the process of dataset selection, feature selection, and explainability.