Car-Following Modeling Incorporating Driving Memory Based on Autoencoder and Long Short-Term Memory Neural Networks

Pengcheng Fan,Haifeng Zhao,Jingqiu Guo,Jasper S Wijnands,Yibing Wang

doi:10.3390/su11236755

Pengcheng Fan, Haifeng Zhao + Show 3 more

Open Access

https://doi.org/10.3390/su11236755

Copy DOI

Abstract

Although a lot of work has been conducted on car-following modeling, model calibration and validation are still a great challenge, especially in the era of autonomous driving. Most challengingly, besides the immediate benefit incurred with a car-following action, a smart vehicle needs to learn to evaluate the long-term benefits and become foresighted in conducting car-following behaviors. Driving memory, which plays a significant role in car-following, has seldom been considered in current models. This paper focuses on the impact of driving memory on car-following behavior, particularly, historical driving memory represents certain types of driving regimes and drivers’ maneuver in coordination with the variety of driving regimes. An autoencoder was used to extract the main features underlying the time-series data in historical driving memory. Long short-term memory (LSTM) neural network model has been employed to investigate the relationship between driving memory and car-following behavior. The results show that velocity, relative velocity, instant perception time (IPT), and time gap are the most relevant parameters, while distance gap is insignificant. Furthermore, we compared the accuracy and robustness of three patterns including various driving memory information and span levels. This study contributes to bridging the gap between historical driving memory and car-following behavior modeling. The developed LSTM methodology has the potential to provide personalized warnings of dangerous car-following distance over the next second.

Highlights

Traffic safety is facing more challenges with the fast development of our society [1]
The results show that velocity, relative velocity, instant perception time (IPT) and time gap are the most relevant parameters, while the distance gap is insignificant
Cetchanandihsmt d,ewnohteerethIet denotes the hidden state input vectors and output of the LSInTMorcdeelrl atot tiamnaelyt.zTehtehesigimanpdacttanohf idnritvhiengfigmureemionrdyicoante CthFe bsteahnadvaiorrd, swigemionivdesatnigdatheypseevrberoallic tanltgeernattfiuvnecmtiondetlrianngsafoprpmroinagchthese. iBnypcuotminptoarriannggtehse[c0o,1r]reasnpdon[−d1in,1g],prersfpoercmtiavneclye. oInf tthheesehimddodenellsa, yweers, thcaenininfoferrmhaotiwonthfleodwrikveinegpsmbeeminogrycoamffpecuttseCdFanbedhuapvdioartseadt, dpiafsfesrinengtthtiomuegshptahnes.Long short-term memory (LSTM) cells one by one until tFhiegufirnea5l psrheodwicstitohnrseearaepopbrtoaaincheeds.(patterns) we investigated in CF models

Summary

Introduction

Traffic safety is facing more challenges with the fast development of our society [1]. Car-following (CF) and lane-changing behaviors can partly account for observed traffic phenomena, such as traffic oscillation and capacity drop, and they are highly associated with the traffic safety risks [2,3]. In the past few years, many studies focused on modeling car-following and lane-changing behaviors to investigate the underlying mechanism of traffic phenomena in detail, e.g., the Gazis-Herman-Rothery (GHR) model, full velocity difference model [4] and intelligent driver model (IDM) [5]. Most models capture traffic characteristics and drivers’ car-following behaviors well if correctly calibrated, but limitations remain. Many data-driven car-following models use machine learning techniques such as random forests, gated recurrent unit (GRU) neural networks, and reinforcement learning (RL), to predict driver actions given a specific traffic environment

Objectives

Results

Conclusion