Junyi Ji 🌱
@jijunyi.bsky.social
Enjoy transportation and dynamic systems. Open Traffic Science. Views are my own.
When I see posts claiming 15 or 20 papers for presentation at the TRB Annual Meeting, the peer pressure is undeniable. It's easy to get caught up in the race for quantity.
But it begs the question: At what cost to quality?
But it begs the question: At what cost to quality?
November 3, 2025 at 2:24 AM
When I see posts claiming 15 or 20 papers for presentation at the TRB Annual Meeting, the peer pressure is undeniable. It's easy to get caught up in the race for quantity.
But it begs the question: At what cost to quality?
But it begs the question: At what cost to quality?
We may need tell the world a message: don't dream of RL for real-time signal control (in practice)! Multiple reasons...
October 26, 2025 at 5:34 AM
We may need tell the world a message: don't dream of RL for real-time signal control (in practice)! Multiple reasons...
Preliminary findings from the field experiments (conducted jointly with and led by JRC colleagues) on commercial L2+ automated vehicles show that their lane-changing behavior is surprisingly consistent.
Safety Perspective on Assisted Lane Changes: Insights from Open-Road, Live-Traffic Experiments
This study investigates the assisted lane change functionality of five different vehicles equipped with advanced driver assistance systems (ADAS). The goal is to examine novel, under-researched featur...
arxiv.org
October 8, 2025 at 11:53 PM
Preliminary findings from the field experiments (conducted jointly with and led by JRC colleagues) on commercial L2+ automated vehicles show that their lane-changing behavior is surprisingly consistent.
I highly recommend Prof. Benn Coifman’s talk. When discussing the fundamental relationship in traffic dynamics, let's first check how the data is generated.
youtu.be/4oZM68VEkfE?...
youtu.be/4oZM68VEkfE?...
Questioning fundamental traffic flow theory assumption
YouTube video by Ammar Dado
youtu.be
October 8, 2025 at 11:49 PM
I highly recommend Prof. Benn Coifman’s talk. When discussing the fundamental relationship in traffic dynamics, let's first check how the data is generated.
youtu.be/4oZM68VEkfE?...
youtu.be/4oZM68VEkfE?...
Back in 2015 (as an undergrad), I felt long-horizon traffic planning would not be the priority, we needed fine-grained, high-resolution data and research. Now, 10 years later, enabled by GenAI, we can finally move from coarse minute-level analysis down to the second level.
tinyurl.com/trafficwavex
tinyurl.com/trafficwavex
October 8, 2025 at 11:45 PM
Back in 2015 (as an undergrad), I felt long-horizon traffic planning would not be the priority, we needed fine-grained, high-resolution data and research. Now, 10 years later, enabled by GenAI, we can finally move from coarse minute-level analysis down to the second level.
tinyurl.com/trafficwavex
tinyurl.com/trafficwavex
After two years of effort, this study has now been accepted through peer review. In nowdays era of massive vehicle trajectory data, it is time to revisit how we analyze and understand traffic waves. I created a gallery with hundreds of traffic waves: trafficwaves.github.io.
arxiv.org/abs/2409.00326
arxiv.org/abs/2409.00326
Scalable analysis of stop-and-go waves: Representation, measurements and insights
Analyzing stop-and-go waves at the scale of miles and hours of data is an emerging challenge in traffic research. The past 5 years have seen an explosion in the availability of large-scale traffic dat...
arxiv.org
October 8, 2025 at 11:36 PM
After two years of effort, this study has now been accepted through peer review. In nowdays era of massive vehicle trajectory data, it is time to revisit how we analyze and understand traffic waves. I created a gallery with hundreds of traffic waves: trafficwaves.github.io.
arxiv.org/abs/2409.00326
arxiv.org/abs/2409.00326
I really enjoyed this paper, although I’m an outsider to Transportation Network Modeling. My main takeaway is clear: as more data becomes available, we should advance toward analyzing more complex networks, rather than continuing to benchmark solely on Sioux Falls.
arxiv.org/abs/2508.06234
arxiv.org/abs/2508.06234
Rethinking the Sioux Falls Network: Insights from Path-Driven Higher-Order Network Analysis
Benchmark scenarios are widely used in transportation research to evaluate routing algorithms, simulate infrastructure interventions, and test new technologies under controlled conditions. However, th...
arxiv.org
October 8, 2025 at 11:34 PM
I really enjoyed this paper, although I’m an outsider to Transportation Network Modeling. My main takeaway is clear: as more data becomes available, we should advance toward analyzing more complex networks, rather than continuing to benchmark solely on Sioux Falls.
arxiv.org/abs/2508.06234
arxiv.org/abs/2508.06234
It's great that we can post dataset and code link in the paper article info now!
September 16, 2025 at 1:51 AM
It's great that we can post dataset and code link in the paper article info now!
I'm always amazed by traffic research history. This is a highway test track at Ohio State University in 1969.
August 10, 2025 at 12:18 PM
I'm always amazed by traffic research history. This is a highway test track at Ohio State University in 1969.
Don't chase for buzzword! First principle matters.
August 4, 2025 at 4:38 PM
Don't chase for buzzword! First principle matters.
Transportation is an application-driven field. Follow the first principle and solve the problems. We don't need more problems but we need more problem-solvers.
July 13, 2025 at 3:33 PM
Transportation is an application-driven field. Follow the first principle and solve the problems. We don't need more problems but we need more problem-solvers.
Our 2nd Trajectory Data Camp at ITSC 2025! This year’s focus is on safety and human factors, and I wish to help drive the Vision Zero moonshot.
Trajectory Data Camp at ITSC 2025 | I-24 MOTION
Testbed for traffic management and automated vehicle technologiesLocated on 4 miles of Interstate 24 in Middle Tennessee
i24motion.org
July 4, 2025 at 8:15 PM
Our 2nd Trajectory Data Camp at ITSC 2025! This year’s focus is on safety and human factors, and I wish to help drive the Vision Zero moonshot.
Legacy NGSIM I-80 is now so real in Google Maps 3D view!!!
June 14, 2025 at 6:33 PM
Legacy NGSIM I-80 is now so real in Google Maps 3D view!!!
I have to say, TRB is where I truly grew as a researcher.
June 3, 2025 at 5:24 PM
I have to say, TRB is where I truly grew as a researcher.
I’ll be at the TRB DATA conference as well! Just to mention, my advisor Dan Work has been my long-time supporter on reproducible research. And we’re actively contributing to open data in traffic science.
May 26, 2025 at 7:08 PM
I’ll be at the TRB DATA conference as well! Just to mention, my advisor Dan Work has been my long-time supporter on reproducible research. And we’re actively contributing to open data in traffic science.
Reposted by Junyi Ji 🌱
📣 I will be giving two talks this week at the TRB DATA conference in Seattle, which explores the intersection of transportation, artificial Intelligence, and data analysis. I love these practitioner + researcher conferences. 🤖🧠👇
May 26, 2025 at 6:02 PM
📣 I will be giving two talks this week at the TRB DATA conference in Seattle, which explores the intersection of transportation, artificial Intelligence, and data analysis. I love these practitioner + researcher conferences. 🤖🧠👇
Reposted by Junyi Ji 🌱
📣 #RERITE 's first conference presentation will take place tomorrow at the Transportation Research Symposium at Rotterdam in The Netherlands! 🚂🛣️
We use Large Language Models (LLMs) to measure the state of data & code availability in transportation research. Join to learn: 👇
We use Large Language Models (LLMs) to measure the state of data & code availability in transportation research. Join to learn: 👇
May 25, 2025 at 9:35 PM
📣 #RERITE 's first conference presentation will take place tomorrow at the Transportation Research Symposium at Rotterdam in The Netherlands! 🚂🛣️
We use Large Language Models (LLMs) to measure the state of data & code availability in transportation research. Join to learn: 👇
We use Large Language Models (LLMs) to measure the state of data & code availability in transportation research. Join to learn: 👇
In memory of Peter Lax (1926–2025).
I will dedicate myself to advancing the next chapter in the applications of hyperbolic partial differential equations in traffic flow dynamics.
www.nytimes.com/2025/05/16/s...
I will dedicate myself to advancing the next chapter in the applications of hyperbolic partial differential equations in traffic flow dynamics.
www.nytimes.com/2025/05/16/s...
Peter Lax, Pre-eminent Cold War Mathematician, Dies at 99
www.nytimes.com
May 17, 2025 at 8:51 PM
In memory of Peter Lax (1926–2025).
I will dedicate myself to advancing the next chapter in the applications of hyperbolic partial differential equations in traffic flow dynamics.
www.nytimes.com/2025/05/16/s...
I will dedicate myself to advancing the next chapter in the applications of hyperbolic partial differential equations in traffic flow dynamics.
www.nytimes.com/2025/05/16/s...
You can be sad but please never be discouraged.
May 10, 2025 at 7:45 PM
You can be sad but please never be discouraged.
My first research grant!
Our student team awarded Lacy-Fischer Interdisciplinary research grant on freeway safety
lab-work.github.io
May 4, 2025 at 10:26 PM
My first research grant!
At the end of a paper [1] by Newell: Will we better in the next 50 years?
[1] Newell, Gordon F. "Memoirs on highway traffic flow theory in the 1950s." Operations Research 50, no. 1 (2002): 173-178.
[1] Newell, Gordon F. "Memoirs on highway traffic flow theory in the 1950s." Operations Research 50, no. 1 (2002): 173-178.
May 2, 2025 at 11:55 PM
At the end of a paper [1] by Newell: Will we better in the next 50 years?
[1] Newell, Gordon F. "Memoirs on highway traffic flow theory in the 1950s." Operations Research 50, no. 1 (2002): 173-178.
[1] Newell, Gordon F. "Memoirs on highway traffic flow theory in the 1950s." Operations Research 50, no. 1 (2002): 173-178.
Reposted by Junyi Ji 🌱
🚦Inaugural Steering Committee of #RERITE 🚦
Dr. @cathywu.bsky.social
Dr. Xuesong (Simon) Zhou & Dr. Bidisha Ghosh
Dr. Silvia Francesca Varotto & Dr. Bahman Madadi
Dr. Yanbing Wang
Dr. Michalis Makridis
🌐 www.rerite.org
🔗 lnkd.in/d38VqpdM
#OpenScience #Reproducibility #Transportation
Dr. @cathywu.bsky.social
Dr. Xuesong (Simon) Zhou & Dr. Bidisha Ghosh
Dr. Silvia Francesca Varotto & Dr. Bahman Madadi
Dr. Yanbing Wang
Dr. Michalis Makridis
🌐 www.rerite.org
🔗 lnkd.in/d38VqpdM
#OpenScience #Reproducibility #Transportation
www.rerite.org
April 11, 2025 at 1:40 PM
🚦Inaugural Steering Committee of #RERITE 🚦
Dr. @cathywu.bsky.social
Dr. Xuesong (Simon) Zhou & Dr. Bidisha Ghosh
Dr. Silvia Francesca Varotto & Dr. Bahman Madadi
Dr. Yanbing Wang
Dr. Michalis Makridis
🌐 www.rerite.org
🔗 lnkd.in/d38VqpdM
#OpenScience #Reproducibility #Transportation
Dr. @cathywu.bsky.social
Dr. Xuesong (Simon) Zhou & Dr. Bidisha Ghosh
Dr. Silvia Francesca Varotto & Dr. Bahman Madadi
Dr. Yanbing Wang
Dr. Michalis Makridis
🌐 www.rerite.org
🔗 lnkd.in/d38VqpdM
#OpenScience #Reproducibility #Transportation
Imaging that we have a perfect, well-calibrated car-following model, what's the best thing you can do with it?
April 12, 2025 at 9:17 PM
Imaging that we have a perfect, well-calibrated car-following model, what's the best thing you can do with it?
it’s probably the best book I get this year!
February 28, 2025 at 2:30 AM
it’s probably the best book I get this year!