Teaching Vehicles to Anticipate: A Systematic Study on Probabilistic Behavior Prediction Using Large Data Sets

TL;DR

This paper systematically compares machine learning methods for probabilistic behavior prediction in self-driving cars, demonstrating high accuracy in maneuver classification and lateral position prediction using large real-world datasets.

Contribution

It introduces a comprehensive evaluation of prediction strategies for autonomous vehicles and shows their effectiveness on extensive highway driving data.

Findings

Maneuver classification with AUC > 0.92 within 5 seconds

Median lateral prediction error less than 0.21 meters

Validation on over 30,000 km of highway data

Abstract

By observing their environment as well as other traffic participants, humans are enabled to drive road vehicles safely. Vehicle passengers, however, perceive a notable difference between non-experienced and experienced drivers. In particular, they may get the impression that the latter ones anticipate what will happen in the next few moments and consider these foresights in their driving behavior. To make the driving style of automated vehicles comparable to the one of human drivers with respect to comfort and perceived safety, the aforementioned anticipation skills need to become a built-in feature of self-driving vehicles. This article provides a systematic comparison of methods and strategies to generate this intention for self-driving cars using machine learning techniques. To implement and test these algorithms we use a large data set collected over more than 30000 km of highway driving and containing approximately 40000 real-world driving situations. We further show that it is possible to classify driving maneuvers upcoming within the next 5 s with an Area Under the ROC Curve (AUC) above 0.92 for all defined maneuver classes. This enables us to predict the lateral position with a prediction horizon of 5 s with a median lateral error of less than 0.21 m.