Driver Behavior Modeling

Driver Behavior Modeling:

Studying the data recorded from vehicles driven by humans reveals that a human driver’s behavior consists of certain patterns and micro-maneuvers. Extracting abstract models of these micro-maneuvers enables us to reliably predict the motion and dynamics of a human-driven vehicles. We particularly focus on two approaches: 1) a stochastic hybrid system based on Gaussian and Dirichlet processes and 2) a data-driven model trained on our D2CAV driving dataset.

Publications:

A Stochastic Hybrid Framework for Driver Behavior Modeling Based on Hierarchical Dirichlet Process

Hossein Nourkhiz Mahjoub, Behrad Toghi, Yaser P Fallah

2018 IEEE 88th Vehicular Technology Conference (VTC2018-Fall), Chicago, IL

A Driver Behavior Modeling Structure Based on Non-parametric Bayesian Stochastic Hybrid Architecture

Hossein Nourkhiz Mahjoub, Behrad Toghi, Yaser P Fallah

2018 IEEE 88th Vehicular Technology Conference (VTC2018-Fall), Chicago, IL

V2X System Architecture Utilizing Hybrid Gaussian Process-Based Model Structures

Hossein Nourkhiz Mahjoub, Behrad Toghi, SM Osman Gani, Yaser P Fallah

2019 IEEE International Systems Conference (SysCon)

A Maneuver-based Urban Driving Dataset and Model for Cooperative Vehicle Applications

Behrad Toghi, Divas Grover, Mahdi Razzaghpour, Rajat Jain, Rodolfo Valiente, Mahdi Zaman, Ghayoor Shah, Yaser P. Fallah

IEEE Connected & Automated Vehicle Symposium (IEEE CAVS 2020)

Posters:

NSF PI Meeting, Washington, D.C.

Our work on driver behavior modeling presented at the Annual National Science Foundation PI meeting. “Multi-resolution Model and Context Aware Information Networking for Cooperative Vehicle Efficiency and Safety Systems”

AVS 2019, Orlando, FL, USA

We introduce the D2CAV dataset: a real-world maneuver-based driving dataset that is collected during our urban driving data collection campaign and labeled by maneuvers in real-time by a human annotator.

Behrad Toghi Behrad Toghi Behrad Toghi Behrad Toghi