Learning an Interpretable Model for Driver Behavior Prediction with Inductive Biases

TL;DR

This paper introduces an interpretable driver behavior prediction model that combines deep neural networks with the Intelligent Driver Model, achieving accurate, transparent predictions suitable for autonomous vehicle planning.

Contribution

It embeds a rule-based driver model into neural networks to enhance interpretability without sacrificing predictive accuracy in driving scenarios.

Findings

The model provides transparent predictions that are easier to interpret.

It maintains high accuracy comparable to black-box neural networks.

The approach is end-to-end trainable and robust in simulated merging scenarios.

Abstract

To plan safe maneuvers and act with foresight, autonomous vehicles must be capable of accurately predicting the uncertain future. In the context of autonomous driving, deep neural networks have been successfully applied to learning predictive models of human driving behavior from data. However, the predictions suffer from cascading errors, resulting in large inaccuracies over long time horizons. Furthermore, the learned models are black boxes, and thus it is often unclear how they arrive at their predictions. In contrast, rule-based models, which are informed by human experts, maintain long-term coherence in their predictions and are human-interpretable. However, such models often lack the sufficient expressiveness needed to capture complex real-world dynamics. In this work, we begin to close this gap by embedding the Intelligent Driver Model, a popular hand-crafted driver model, into deep neural networks. Our model's transparency can offer considerable advantages, e.g., in debugging the model and more easily interpreting its predictions. We evaluate our approach on a simulated merging scenario, showing that it yields a robust model that is end-to-end trainable and provides greater transparency at no cost to the model's predictive accuracy.