Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

TL;DR

This paper investigates how a neural network trained end-to-end for autonomous driving makes steering decisions, revealing that it learns both obvious and subtle road features influencing its behavior.

Contribution

The authors develop a method to interpret neural network decisions, demonstrating that PilotNet learns relevant and subtle features from road images for steering.

Findings

PilotNet recognizes key road features like lane markings and cars.

It also learns subtle cues such as roadside bushes and unusual vehicle types.

The method helps explain neural network decision-making in autonomous driving.

Abstract

As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by observing human drivers. This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving. Road tests demonstrated that PilotNet can successfully perform lane keeping in a wide variety of driving conditions, regardless of whether lane markings are present or not. The goal of the work described here is to explain what PilotNet learns and how it makes its decisions. To this end we developed a method for determining which elements in the road image most influence PilotNet's steering decision. Results show that PilotNet indeed learns to recognize relevant objects on the road. In addition to learning the obvious features such as lane markings, edges of roads, and other cars, PilotNet learns more subtle features that would be hard to anticipate and program by engineers, for example, bushes lining the edge of the road and atypical vehicle classes.