Poster presentation on human-like autonomous car following at the 97th TRB annual meeting.
Meixin Zhu is a Ph.D. candidate in intelligent transportation at the University of Washington. He also serves as a research assistant in Smart Transportation Applications and Research Laboratory (STAR Lab) at the University of Washington, advised by Prof. Yinhai Wang. Before joining STAR Lab, he served as a research assistant in Tongji’s Traffic Safety Research Group, advised by Prof. Xuesong Wang from 2014 to 2018. He is currently a research intern at the Oak Ridge National Laboratory under the supervision of Prof. Hong Wang.
Zhu’s research interests include computer vision, lidar 3d detection, autonomous driving decision making, reinforcement learning, big data analytics, driving behavior, traffic-flow modeling and simulation, and naturalistic driving study. Zhu acts as a reviewer for the Thirty-seventh International Conference on Machine Learning (ICML 2020), the IEEE Transactions on Intelligent Vehicles and the top traffic safety journal: Accident Analysis & Prevention (IF: 3.058). He is a younger committee member of the Connected & Autonomous Vehicles (CAV) Impacts Committee of ASCE Transportation & Development. He has been awarded China National Graduate Scholarship (top 0.2%) twice and was the winner of Outstanding Student Award at Tongji University for 2016, as well as the Outstanding Graduates of Shanghai (top 5% among all graduates in Shanghai) (Last updated in Nov. 2019).
Here is a demo video for his autonomous racecar research.
Ph.D. in Transportation Engineering, 2022 (expected)
University of Washington
MEng in Communication and Transportation Engineering, 2018
BEng in Traffic Engineering, 2015
For a most recent publication list, please refer to my CV.
The first large-scale naturalistic driving study in China. A total of 161,055 km of real-world detailed driving data were collected from 60 Chinese drivers, providing an unprecedented opportunity for investigating driving behavior in China.
AlphaDrive is a platform equipped with real-world driving scenarios where intelligent agents can learn to drive by trial and error, trials and errors that number in the billions.
A driving simulator study jointly conducted by Tongji University and China First Automobile Work Corporation. Tongji University’s eight-degree-freedom driving simulator (its fidelity ranking top 3 in the world) was used. Its primary purpose is to improve the understanding of drivers’ collision avoidance behavior under different rear-end scenarios and to develop an effective forward collision warning strategy.
Udacity’s Self-Driving Car Engineer Nanodegree Program offered 12 autonomous-driving-related projects and covered topics including deep learning, computer vision, sensor fusion, localization, controllers, vehicle kinematics, automotive hardware.
This on-going project aims to develop autonomous car-following strategies based on deep reinforcement learning.The demo animation shows the car-following learning process of the RL agents (cars). In early training episodes, cars become red frequently, indicating penalties caused by bad performances in car following, e.g., rear-end crashes. As training converges, the RL agents maintain steady car-following headways and receive fewer penalties.
This on-going project is inspired by NVIDIA’s research (1) and MIT 6.S094’s DeepTesla project (2). It aims to learn human drivers’ strategy in steering control. The learned model can map raw pixels from a single front-facing camera directly to steering commands.
This on-going project is inspired by Levine et al. (2012). It aims to imitate human driving patterns. The assumption is that drivers act based on a utility (reward) function, which represents the preference of the driver and elicits the driving behavior. The role of inverse reinforcement learning is to infer or discover the latent utility function from driver (expert) demonstrations and thus generalize the driving policy to unobserved situations.
This project aimed to segment different moving objects in a video sequence, using subspace clustering methods.
This project aimed to extract real-time traffic flow parameters, including volume, density, and intersection delay, etc., based on videos captured by an unmanned aerial vehicle. The featured animation demonstrates the extraction of traffic-flow parameters by setting virtual loop detectors.
This project aimed to model the keep-right-except-to-pass rule using Cellular Automaton. The cellular automaton system is a discrete dynamic system consisting of a regular grid of cells, each in one of a finite number of states. And the state of each cell is updated every single discrete time step according to the updating rules, which are determined by the current state of the cell and the states of its neighbor cells.
Evaluating the safety performance of combined horizontal and vertical alignments in mountainous freeways, to guide the design of safer mountainous freeways.
Shanghai Naturalistic Driving Study collected 60 Chinese drivers’ daily driving data, with a total mileage of 161,055 km. These data provide an unprecedented opportunity for investigating driving behavior in China.
Extracted 108,933 car-following events, and investigated the distribution of drivers’ car-following gaps and headways.
Extracted 17,309 lane-change events, and investigated the frequency, motivations, gazing behavior, and turn-signal usages for lane-change behavior.
Extracted 7,845 cut-in events, and analyzed cut-in purposes, turn signal usages, cut-in duration and urgency. (Paper: An Exploration of Cut-In Behavior and Gap Acceptance Using Shanghai Naturalistic Driving Data)
In Driving Behavior Research for Intelligent Collision Avoidance Technology, a high fidelity driving simulator was used to examine the effects of differing levels of situational urgency on drivers’ collision avoidance behaviors. (Paper: Drivers’ Rear End Collision Avoidance Behaviors under Different Levels of Situational Urgency)
Based on the Shanghai Naturalistic Driving Study data, drivers’ phone-use characteristics and the influence of phone use on driving performance were examined.
The impact of the FCW system on drivers’ car-following behaviors was investigated. (Paper: Impact of a Forward Collision Warning System on Headway and Reaction Time during Car Following)
In Optimized Design for Combined Road Alignment, the effects of combined alignments on driving behavior (e.g., speed and lateral acceleration) and safety performance (crash surrogate measures like lane departure events and emergency braking events) were examined using driving simulator and field data. The results will assist engineers to design safer mountainous freeways.
The performances of existing car-following models applied to Chinese drivers were evaluated. (Paper: Calibrating and Validating Car-Following Models on Urban Expressways for Chinese Drivers Using Naturalistic Driving Data)
To evaluate the performance of the keep-right-except-to-pass rule in traffic systems, the cellular automaton method was applied to simulate traffic flows in one-lane, two-lane and three-lane freeways. The results showed that the model could replicate volume-density relationship well.
In Autonomous Car Following by Deep Reinforcement Learning, two types of autonomous car-following strategies were developed based on deep reinforcement learning (RL).
Historical driving data are fed into a simulation environment, where an RL agent learns from trying and interaction, with a reward function signaling how much the agent deviates from the empirical data. Results showed that this new model can reproduce human-like car-following behavior with significantly higher accuracy than traditional car-following models, especially regarding speed replicating. (Paper: Human-like Autonomous Car-Following Planning by Deep Reinforcement Learning)
To fulfill the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With this reward function, the RL agent learns to control vehicle speed in a fashion that maximizes cumulative rewards, through trials and errors in the simulation environment. Results showed that the model demonstrated the capability of safe, efficient, and comfortable velocity control. (Paper: Reinforcement Learning based Velocity Control for Autonomous Driving with Multi-Objectives: Safety, Efficiency, and Comfort)
Current autonomous driving decision-making algorithms mainly focus on interactions between passenger cars, while the interactions between large vehicles, non-motor vehicles, and pedestrians are rarely taken into account. However, the mixture of different transport modes is just the critical feature of Chinese urban traffic. Therefore, this on-going research aims to develop and test autonomous driving algorithms for mixed traffic environments. The following steps will be followed:
Poster presentation on human-like autonomous car following at the 97th TRB annual meeting.
During September 25 and 26, 2017, the Fifth International Symposium on Transportation Safety was held at Tongji University. Over 200 scholars and experts from research institutions and government agencies attended the symposium. Zhu served as a volunteer for the meeting organizing.
Oral presentation on car-following model calibration at the 96th TRB annual meeting.
Attending the top international symposium on naturalistic driving study, one of my major research interests.
Coming across one of the world’s most well-known transportation scientists, Carlos F. Daganzo, at the 16th COTA International Conference of Transportation Professionas.