InterSim: Innovative Intersection Digital Twins for Human-in-the-Loop Driving Simulation

Luyang Jiang1, Chuheng Wei1, Yaguang Li1, Shaoqi Wang1, Yupeng Zhou1, Hyunsoo Yun1, Xishun Liao2, Brandon Pitts1, Ziran Wang1,✉

1College of Engineering, Purdue University 2College of Engineering, University of Central Florida ✉Corresponding author: ziran@ieee.org

Demo video coming soon

Abstract

Innovative intersection designs can improve roadway safety and operational efficiency, but their uncommon geometries may create challenges for driver comprehension during early deployment. Evaluating these designs through full-scale field implementation can also be costly. This paper presents InterSim, a Unity game engine-based human-in-the-loop (HITL) driving simulator that constructs digital twins of site-specific innovative intersections in a virtual environment. InterSim links the real world and the simulation world through two closed cycles: a digital twin cycle that builds each intersection twin from agency design and traffic data and returns evidence from simulation to the agency, and an HITL cycle in which human drivers or automated driving algorithms operate the ego vehicle under identical scenario conditions. The research capabilities of InterSim are demonstrated through two case studies: a surrogate safety study compares post-encroachment time distributions between a Reduced Conflict Intersection and a conventional intersection under different traffic volumes; an eco-driving study compares human drivers with a rule-based agent using vehicle-to-infrastructure information and reveals differences in emission and driving behavior. These studies demonstrate that InterSim provides a reusable digital twin platform for investigating innovative intersection designs from diverse perspectives.

Why InterSim?

The design

Innovative intersections use paths that first-time drivers find confusing

The cost

Testing a layout in the field is costly and puts road users at risk

The gap

Traffic and driving simulators leave out how humans drive a new design

System Architecture

InterSim couples the real world, where agencies hold the design data and drivers operate vehicles, with a simulation world that keeps a digital twin of each intersection. Two closed cycles connect them.

InterSim architecture. Real world: engineering documents, HD maps, traffic data, infrastructure owner-operators, human and automated drivers. Simulation world: five intersection digital twins (DLT, RCI, RBI, DDI, RAB), traffic generation module, analysis module, and ego vehicle platform.

Intersection Digital Twins

Each twin is modeled from agency road-plan documents and aerial imagery. It keeps the real site's road geometry, pavement markings, traffic signs, and signals, so a driver sees the same visual guidance and maneuvers as at the real intersection. InterSim currently includes five innovative intersection twins.

DLT

Displaced Left Turn

Left-turning traffic crosses the opposing lanes upstream of the main intersection, so left turns can run at the same time as opposing through traffic.

Real world vs. InterSim

Drag the handle to compare the aerial image of the real site with the digital twin.

Roundabout Interchange in InterSim
Roundabout Interchange, aerial image of the real site
Real InterSim

From the driver's seat

In-cabin view of a human driver waiting at a signal in the InterSim DLT digital twin
A human driver waits at the signal of the Displaced Left Turn twin, driving with a steering wheel and pedals.

Vehicles

Ego-vehicle physics expose engine characteristics, gear ratios, suspension, and tire friction, so they can be tuned to match a production vehicle. InterSim currently includes four types of vehicles.

Honda CR-VSUV
Lexus RCCoupe
RAM 1500Pickup truck
Toyota CamrySedan

Citation

@misc{jiang2026intersim,
  title  = {InterSim: Innovative Intersection Digital Twins for
            Human-in-the-Loop Driving Simulation},
  author = {Jiang, Luyang and Wei, Chuheng and Li, Yaguang and
            Wang, Shaoqi and Zhou, Yupeng and Yun, Hyunsoo and
            Liao, Xishun and Pitts, Brandon and Wang, Ziran},
  year   = {2026}
}

Acknowledgement

This work was supported by the Indiana Department of Transportation (INDOT) Joint Transportation Research Program (JTRP) under Grant JTRP-4932.