ForSim logo

ForSim: Forward Simulation for Realistic Interactive Traffic Scenarios

Keyu Chen1    Wenchao Sun1    Hao Cheng1    Zheng Fu1    Sifa Zheng1
1School of Vehicle and Mobility, Tsinghua University
ICRA 2026
arXiv Code(Coming Soon)

ForSim is a forward-simulation framework designed to synthesize realistic, interactive traffic scenarios for closed-loop AV evaluation. It decouples scene rollout from trajectory alignment, enabling controllable yet natural interactions across diverse map topologies.

ForSim intro overview
ForSim trajectory alignment

Abstract

As the foundation of closed-loop training and evaluation in autonomous driving, traffic simulation still faces two fundamental challenges: covariate shift introduced by open-loop imitation learning and limited capacity to reflect the multimodal behaviors observed in real-world traffic. Although recent frameworks such as RIFT have partially addressed these issues through group-relative optimization, their forward simulation procedures remain largely non-reactive, leading to unrealistic agent interactions within the virtual domain and ultimately limiting simulation fidelity. To address these issues, we propose ForSim, a stepwise closed-loop forward simulation paradigm. At each virtual timestep, the traffic agent propagates the virtual candidate trajectory that best spatiotemporally matches the reference trajectory through physically grounded motion dynamics, thereby preserving multimodal behavioral diversity while ensuring intra-modality consistency. Other agents are updated with stepwise predictions, yielding coherent and interaction-aware evolution. When incorporated into the RIFT traffic simulation framework, ForSim operates in conjunction with group-relative optimization to fine-tune traffic policy. Extensive experiments confirm that this integration consistently improves safety while maintaining efficiency, realism, and comfort. These results underscore the importance of modeling closed-loop multimodal interactions within forward simulation and enhance the fidelity and reliability of traffic simulation for autonomous driving.

Method Overview

Basic rollout

Basic Rollout

Predict multi-agent rollouts with open-loop dynamics as an initial proposal set.

Step rollout

Step Rollout

Refine agent states step-by-step to capture short-horizon interaction cues.

ForSim pipeline

Scenario Gallery

Urban Intersection Interaction

Dense Lane Merging

Curved-Lane Following

Multi-Agent Overtake

High-Speed Straight Driving

Intersection Navigation

Quantitative Results

ForSim results

ForSim improves interaction realism and alignment stability across long-horizon rollouts, enabling robust benchmarking of AV planners and end-to-end driving stacks.

BibTeX

If you find the project helpful for your research, please consider citing our paper: 
@misc{chen2026forsimstepwiseforwardsimulation,
      title={ForSim: Stepwise Forward Simulation for Traffic Policy Fine-Tuning}, 
      author={Keyu Chen and Wenchao Sun and Hao Cheng and Zheng Fu and Sifa Zheng},
      year={2026},
      eprint={2602.01916},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2602.01916}, 
}