# A Generative Model for Closed-Loop Microsimulation of Signalized Intersections

arXiv: https://arxiv.org/abs/2606.23588 · HTML: https://mlsanity.com/paper/2606.23588/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [Convolutional Social Pooling for Vehicle Trajectory Prediction](https://mlsanity.com/paper/1805.06771/) (2018)
- [HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding](https://mlsanity.com/paper/2205.09753/) (2022)
- [The Waymo Open Sim Agents Challenge](https://mlsanity.com/paper/2305.12032/) (2023)
- [TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction](https://mlsanity.com/paper/2303.04116/) (2023)
- [SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model](https://mlsanity.com/paper/2506.21976/) (2025)
- [Building Transportation Foundation Model via Generative Graph Transformer](https://mlsanity.com/paper/2305.14826/) (2023)
- [D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights](https://mlsanity.com/paper/2207.10398/) (2022)
- [TransWorldNG: Traffic Simulation via Foundation Model](https://mlsanity.com/paper/2305.15743/) (2023)
- [Relative Position Matters: Trajectory Prediction and Planning with Polar Representation](https://mlsanity.com/paper/2508.11492/) (2025)
- [Impact of Traffic Lights on Trajectory Forecasting of Human-driven Vehicles Near Signalized Intersections](https://mlsanity.com/paper/1906.00486/) (2019)
- [IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections](https://mlsanity.com/paper/2506.08957/) (2025)
- [Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics](https://mlsanity.com/paper/2506.08963/) (2025)
- [Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving](https://mlsanity.com/paper/2508.01922/) (2025)
- [Enactor: From Traffic Simulators to Surrogate World Models](https://mlsanity.com/paper/2603.18266/) (2026)
- [Beyond Centrality: Understanding Urban Street Network Typologies Through Intersection Patterns](https://mlsanity.com/paper/2511.06747/) (2025)

## Abstract (arXiv)

Traffic microsimulators rely on hand-crafted behavior models that reproduce aggregate flow but miss the heterogeneous interactions between vehicles at signalized intersections. Learned trajectory predictors capture richer interactions but are short-horizon and tend to be unstable when run in closed loop. We present Enactor, an actor-centric generative model for closed-loop intersection microsimulation. The model focuses on vehicles; pedestrians are included as context that can influence vehicle decisions but not predicted. Dynamic actors and lane polylines are encoded in polar coordinates referenced to the intersection center. A transformer with separate spatial and temporal attention blocks predicts a distribution over each actor's next-step motion (s, α). Training uses a closed-loop curriculum so the model is exposed to its own predictions. We evaluate Enactor in two regimes. In a 4000-second simulation-in-the-loop test at two intersection geometries, Enactor controls every dynamic vehicle against a continuously refreshing actor set rather than the fixed cohort that learned trajectory predictors are usually evaluated against. It recovers the SUMO data generator's speed and travel-time distributions with KL divergence over an order of magnitude lower than a recent transformer baseline on travel time, and substantially lower on speed (roughly 5× lower at Site 1), and reduces red-light violations relative to the same baseline by more than an order of magnitude. An ablation isolates the leader rear-bumper feature as the change with the largest effect on intersection-aware safety metrics. We also evaluate on real-world field data and apply the same architecture to naturalistic vehicle trajectories from a fish-eye camera at a signalized intersection and evaluate it on multi-horizon predictive tasks. Enactor outperforms a constant-velocity baseline at every horizon evaluated.