MOTIF Lab

Hao Zhou

Mon, 01 Jan 0001 00:00:00 +0000

Hao Zhou is an Assistant Professor of Transportation Engineering at the University of South Florida, where he leads the MOTIF Lab. His research bridges classical traffic flow theory with frontier vehicle and AI technologies, asking how new vehicle capabilities — adaptive cruise control, lane-keeping assist, electric powertrains — reshape macroscopic traffic efficiency and safety, and how AI tools such as dash-cam vision can extend our ability to observe and manage road networks.

OpenLKA: open dataset of lane keeping assist from market autonomous vehicles

Mon, 01 Jan 0001 00:00:00 +0000

What it is

OpenLKA is the first open benchmark dataset of lane-keeping-assist (LKA) behavior collected from a wide range of production autonomous vehicles in real driving. Released in January 2025, it pairs CAN-bus signals with synchronized forward-facing video and lane-perception output, captured across multiple market vehicles under varied roadway and weather conditions in the Tampa, Florida region.

Why it matters

Lane-keeping assist is one of the most widely deployed ADAS features, but its real-world performance is opaque: most public benchmarks are built on simulated environments or single-vehicle test fleets, and the behavior of production LKA systems differs widely between manufacturers. Without an open, multi-vehicle dataset, researchers cannot calibrate microsimulations of mixed-autonomy traffic, evaluate disengagement risk, or model the variance in LKA-equipped vehicle behavior that capacity and safety analyses now have to contend with.

Traffic flow theory

Mon, 01 Jan 0001 00:00:00 +0000

Traffic flow theory remains the structural language of transportation engineering. Our work in this thread strengthens that language for an era in which vehicles are no longer interchangeable units. We study car-following and lane-changing behavior, the conditions under which fundamental diagrams hold or break, and the propagation of disturbances in heterogeneous traffic streams.

Recent questions include: How does the variance in driver behavior — amplified or dampened by ADAS — change capacity at active bottlenecks? When mixed-autonomy traffic violates the assumptions of LWR-class models, what minimal extensions recover predictive power without overfitting? When does signal-control theory remain robust in congested urban networks, and when does it not?

Vehicle technologies and traffic impact

Mon, 01 Jan 0001 00:00:00 +0000

A vehicle is no longer a fixed object in a flow model — it is a moving system whose perception, control, and powertrain shape its behavior. We characterize ADAS-equipped and electric vehicles empirically and analytically, then quantify what their adoption implies for capacity, stability, and safety on existing roadways.

Specific work includes: car-following calibration for production ACC and LKA systems; the energy-efficiency / throughput trade-off introduced by EV speed-power profiles; and how partial market penetration of automated features changes the distribution of headways and the probability of rear-end conflicts. We collaborate with vehicle dynamics researchers and rely on a mix of test-track data, naturalistic driving data, and microsimulation.

AI for mobility

Mon, 01 Jan 0001 00:00:00 +0000

Modern vision and learning systems extend the reach of traditional traffic monitoring. We develop and evaluate AI tools that turn dash-cam video, roadside cameras, and probe data into operational signals — vehicle counts, incident alerts, pavement and roadside hazard detections — at a fraction of the cost of fixed instrumentation.

Our emphasis is not on novelty in the model architecture alone but on closing the loop with traffic operations: what false-positive rate is tolerable for an alert that triggers a maintenance dispatch? How do edge-device and bandwidth constraints shape what is actually deployable? How do we evaluate detection performance against the messy ground truth available from agencies?

Traffic Flow Theory

Mon, 01 Jan 0001 00:00:00 +0000

Course overview

This course presents a comprehensive overview of vehicular traffic flow theory, emerging transportation AI technologies, and their integration in evaluating congestion and determining control strategies.

Starting from the basic concepts that define a traffic stream, the course covers the classical theories — the kinematic wave model, cellular automata, car-following models, and macroscopic traffic flow models. Beyond traditional theory, students are introduced to state-of-the-art traffic and self-driving simulation tools such as SUMO and CARLA, and to contemporary AI techniques including autonomous driving, reinforcement learning, and large language models. Their applications in traffic operations and implications for congestion management are discussed throughout.

AI for Mobility

Mon, 01 Jan 0001 00:00:00 +0000

The full course site is hosted separately at ai4mobility.github.io.

If you are not redirected automatically, click here to continue to the course site.

Yuhang Wang

Mon, 01 Jan 0001 00:00:00 +0000

Shengming Yuan

Mon, 01 Jan 0001 00:00:00 +0000

Abdulaziz Alhuraish

Mon, 01 Jan 0001 00:00:00 +0000

Zidan Shahriar

Mon, 01 Jan 0001 00:00:00 +0000

Pan Pan

Mon, 01 Jan 0001 00:00:00 +0000

The lab coordinator. Provides moral support and occasional code review.

MOTIF Lab website is live

Sun, 10 May 2026 00:00:00 +0000

We launched the MOTIF Lab website. Replace this post with real news as it happens — accepted papers, grant awards, student milestones, talks given.

Cut-in gap acceptance toward autonomous vs. human-driven vehicles: evidence from the Waymo Open Motion Dataset

Sat, 02 May 2026 00:00:00 +0000

BATON: a multimodal benchmark for bidirectional automation transition observation in naturalistic driving

Wed, 01 Apr 2026 00:00:00 +0000

ADAS-TO: a large-scale multimodal naturalistic dataset and empirical characterization of human takeovers during ADAS engagement

Sat, 07 Mar 2026 00:00:00 +0000

OpenLKA: an open dataset of lane keeping assist from production vehicles under real-world driving conditions

Mon, 01 Sep 2025 00:00:00 +0000

Bridging human oversight and black-box driver assistance: vision-language models for predictive alerting in lane keeping assist systems

Sat, 17 May 2025 00:00:00 +0000

Empirical performance evaluation of lane keeping assist on modern production vehicles

Sat, 17 May 2025 00:00:00 +0000

AI-CDA4All: democratizing cooperative autonomous driving for all drivers via affordable dash-cam hardware and open-source AI software

Sat, 10 May 2025 00:00:00 +0000

String instability mitigation of adaptive cruise control without modifying control laws: trajectory shaper and parameter estimation

Sat, 01 Mar 2025 00:00:00 +0000

OpenLKA: an open dataset of lane keeping assist from market autonomous vehicles

Mon, 06 Jan 2025 00:00:00 +0000

Implications of stop-and-go traffic on training learning-based car-following control

Mon, 01 Apr 2024 00:00:00 +0000

Sight distance of automated vehicles considering highway vertical alignments and its implications for speed limits

Fri, 01 Sep 2023 00:00:00 +0000

Fundamental diagrams of commercial adaptive cruise control: worldwide experimental evidence

Thu, 09 Feb 2023 00:00:00 +0000

Congested urban networks tend to be insensitive to signal settings: implications for learning-based control

Sat, 01 Oct 2022 00:00:00 +0000

Empirical study on the acceleration/deceleration constraints under commercial adaptive cruise control

Sat, 01 Oct 2022 00:00:00 +0000

Incorporating driver relaxation into factory adaptive cruise control to reduce lane-change disruptions

Thu, 01 Sep 2022 00:00:00 +0000

Congestion-mitigating MPC design for adaptive cruise control based on Newell's car-following model: history outperforms prediction

Fri, 01 Jul 2022 00:00:00 +0000

Significance of low-level control to string stability under adaptive cruise control: algorithms, theory and experiments

Fri, 01 Apr 2022 00:00:00 +0000

Review of learning-based longitudinal motion planning for autonomous vehicles: implications on traffic congestion

Wed, 01 Sep 2021 00:00:00 +0000

Car-following behavior characteristics of adaptive cruise control vehicles based on empirical experiments

Thu, 01 Apr 2021 00:00:00 +0000

Extracting topographic data from online sources to generate a digital elevation model for highway preliminary geometric design

Mon, 01 Oct 2018 00:00:00 +0000

Hybrid modeling of lane changes near freeway diverges

Sun, 01 Jan 2017 00:00:00 +0000

Numerical study of Bernoulli effect on bus controllability and driving safety

Sun, 01 Jan 2017 00:00:00 +0000

Join us

Mon, 01 Jan 0001 00:00:00 +0000

We are recruiting motivated students who want to do careful, technical research at the intersection of traffic flow theory, vehicle technology, and AI for mobility.

Prospective PhD students

Strong candidates have a background in transportation engineering, civil engineering, mechanical/automotive engineering, computer science, or applied math. We particularly value: solid programming (Python and one of MATLAB/C++/Julia); comfort with mathematical modeling; and curiosity about how vehicles, drivers, and infrastructure jointly produce traffic phenomena. Prior research experience (a thesis, an internship, or a published paper) helps.