Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies

TL;DR

This paper introduces Symbolic Imitation Learning (SIL), a framework that uses Inductive Logic Programming to create explainable and generalizable driving policies, addressing interpretability issues of neural network-based methods in autonomous driving.

Contribution

SIL is the first framework to combine ILP with imitation learning for autonomous driving, improving transparency and generalizability over traditional neural approaches.

Findings

SIL achieves comparable collision rates to neural methods.

SIL improves policy transparency and interpretability.

SIL maintains strong performance across diverse driving scenarios.

Abstract

Current imitation learning approaches, predominantly based on deep neural networks (DNNs), offer efficient mechanisms for learning driving policies from real-world datasets. However, they suffer from inherent limitations in interpretability and generalizability--issues of critical importance in safety-critical domains such as autonomous driving. In this paper, we introduce Symbolic Imitation Learning (SIL), a novel framework that leverages Inductive Logic Programming (ILP) to derive explainable and generalizable driving policies from synthetic datasets. We evaluate SIL on real-world HighD and NGSim datasets, comparing its performance with state-of-the-art neural imitation learning methods using metrics such as collision rate, lane change efficiency, and average speed. The results indicate that SIL significantly enhances policy transparency while maintaining strong performance across varied driving conditions. These findings highlight the potential of integrating ILP into imitation learning to promote safer and more reliable autonomous systems.