Human Driver Behavior Prediction based on UrbanFlow

TL;DR

This paper introduces UrbanFlow, a system for collecting urban driving data, and an LSTM-based method for predicting human driver trajectories to improve autonomous vehicle decision-making at intersections.

Contribution

The paper presents a novel urban data collection system and an LSTM-based trajectory prediction model tailored for urban driving scenarios.

Findings

UrbanFlow effectively captures detailed urban driving behavior.

The LSTM model improves trajectory prediction accuracy.

System can be extended to various traffic environments.

Abstract

How autonomous vehicles and human drivers share public transportation systems is an important problem, as fully automatic transportation environments are still a long way off. Understanding human drivers' behavior can be beneficial for autonomous vehicle decision making and planning, especially when the autonomous vehicle is surrounded by human drivers who have various driving behaviors and patterns of interaction with other vehicles. In this paper, we propose an LSTM-based trajectory prediction method for human drivers which can help the autonomous vehicle make better decisions, especially in urban intersection scenarios. Meanwhile, in order to collect human drivers' driving behavior data in the urban scenario, we describe a system called UrbanFlow which includes the whole procedure from raw bird's-eye view data collection via drone to the final processed trajectories. The system is mainly intended for urban scenarios but can be extended to be used for any traffic scenarios.