Chengyuan Zhang

Chengyuan Zhang
McGill University | McGill · Department of Civil Engineering and Applied Mechanics

Ph.D. Student

About

18
Publications
5,185
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
122
Citations
Citations since 2017
18 Research Items
122 Citations
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
Introduction
Chengyuan Zhang is a Ph.D. student in the Department of Civil Engineering at McGill University. His research interests are in the application of statistical learning (especially probabilistic graphical models) in micro/macro driving behavior analysis, traffic scenario pattern recognition, and scene understanding. Personal website: https://chengyuan-zhang.github.io/
Additional affiliations
September 2019 - January 2020
University of California, Berkeley
Position
  • Researcher
July 2018 - October 2018
Carnegie Mellon University
Position
  • Visiting Student
Education
September 2020 - July 2022
McGill University
Field of study
  • Civil Engineering - Transportation
September 2015 - July 2019
Chongqing University
Field of study
  • Vehicle Engineering

Publications

Publications (18)
Conference Paper
Full-text available
Semantic learning and understanding of multi-vehicle interaction patterns in a cluttered driving environment are essential but challenging for autonomous vehicles to make proper decisions. This paper presents a general framework to gain insights into intricate multi-vehicle interaction patterns from bird's-eye view traffic videos. We adopt a Gaussi...
Conference Paper
Full-text available
Reliable representation of multi-vehicle interactions in urban traffic is pivotal but challenging for autonomous vehicles due to the volatility of the traffic environment, such as roundabouts and intersections. This paper describes a semi-stochastic potential field approach to represent multi-vehicle interactions by integrating a deterministic fiel...
Article
Full-text available
Interpretation of common-yet-challenging interaction scenarios can benefit well-founded decisions for autonomous vehicles. Previous research achieved this using their prior knowledge of specific scenarios with predefined models, limiting their adaptive capabilities. This paper describes a Bayesian nonparametric approach that leverages continuous (i...
Preprint
Full-text available
No human drives a car in a vacuum; she/he must negotiate with other road users to achieve their goals in social traffic scenes. A rational human driver can interact with other road users in a socially-compatible way through implicit communications to complete their driving tasks smoothly in interaction-intensive, safety-critical environments. This...
Preprint
Full-text available
Accurate calibration of car-following models is essential for investigating microscopic human driving behaviors. This work proposes a memory-augmented Bayesian calibration approach, which leverages the Bayesian inference and stochastic processes (i.e., Gaussian processes) to calibrate an unbiased car-following model while extracting the serial corr...
Preprint
Full-text available
Following a leading vehicle is a daily but challenging task because it requires adapting to various traffic conditions and the leading vehicle's behaviors. However, the question `Does the following vehicle always actively react to the leading vehicle?' remains open. To seek the answer, we propose a novel metric to quantify the interaction intensity...
Preprint
Full-text available
Car-following behavior modeling is critical for understanding traffic flow dynamics and developing high-fidelity microscopic simulation models. Most existing impulse-response car-following models prioritize computational efficiency and interpretability by using a parsimonious nonlinear function based on immediate preceding state observations. Howev...
Article
Full-text available
The problem of discovering interpretable dynamic patterns from spatiotemporal data is studied in this paper. For that purpose, we develop a time-varying reduced-rank vector autoregression (VAR) model whose coefficient matrices are parameterized by low-rank tensor factorization. Benefiting from the tensor factorization structure, the proposed model...
Preprint
Full-text available
The problem of broad practical interest in spatiotemporal data analysis, i.e., discovering interpretable dynamic patterns from spatiotemporal data, is studied in this paper. Towards this end, we develop a time-varying reduced-rank vector autoregression (VAR) model whose coefficient matrices are parameterized by low-rank tensor factorization. Benefi...
Preprint
Full-text available
Modern time series datasets are often high-dimensional, incomplete/sparse, and nonstationary. These properties hinder the development of scalable and efficient solutions for time series forecasting and analysis. To address these challenges, we propose a Nonstationary Temporal Matrix Factorization (NoTMF) model, in which matrix factorization is used...
Article
Full-text available
No human drives a car in a vacuum; she/he must negotiate with other road users to achieve their goals in social traffic scenes. A rational human driver can interact with other road users in a socially-compatible way through implicit communications to complete their driving tasks smoothly in interaction-intensive, safety-critical environments. This...
Book
Full-text available
In real-world traffic, rational human drivers can make socially-compatible decisions in complex and crowded scenarios by efficiently negotiating with their surroundings using non-linguistic communications such as gesturing, deictics, and motion cues. Understanding the principles and rules of the dynamic interaction among human drivers in complex tr...
Preprint
Full-text available
Interpretation of common-yet-challenging interaction scenarios can benefit well-founded decisions for autonomous vehicles. Previous research achieved this using their prior knowledge of specific scenarios with predefined models, limiting their adaptive capabilities. This paper describes a Bayesian nonparametric approach that leverages continuous (i...
Preprint
Full-text available
Semantic learning and understanding of multi-vehicle interaction patterns in a cluttered driving environment are essential but challenging for autonomous vehicles to make proper decisions. This paper presents a general framework to gain insights into intricate multi-vehicle interaction patterns from bird's-eye view traffic videos. We adopt a Gaussi...
Article
Full-text available
To solve the difficult parking problem, developing a mechanical parking device is a practical approach. Aiming at longitudinal parking, a novel compact double-stack parking system is put forward based on a 1-DOF (degree of freedom) cam-linkage double-parallelogram mechanism. Due to the unique structure, the whole device can be driven by a single mo...
Preprint
Full-text available
To solve the difficult parking problem, developing mechanical parking device is a practical approach. Aiming at longitudinal parking, a novel compact double-stack parking system is put forward based on a 1-DOF (degree of freedom) cam-linkage double-parallelogram mechanism. Due to the unique structure, the whole device can be driven by a single moto...
Article
Full-text available
The fractional differential equations of the single-degree-of-freedom (DOF) quarter vehicle with a magnetorheological (MR) suspension system under the excitation of sine are established, and the numerical solution is acquired based on the predictor–corrector method. The analysis of phase trajectory, time domain response, and Poincare section shows...

Questions

Question (1)
Question
It's important for autonomous vehicle to evaluate the physical states of drivers and determine a right time to warn drivers when under urgent circumstances.
So, are there any public available datasets describing drivers' pose behavior? Thank you!

Network

Cited By