# TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction

Source: [TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction](<https://www.sota2.com/research/paper/68fa70af1e209131cea4c8a4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:47:58.595Z

Authors: Zhejun Zhang, Alexander Liniger, Dengxin Dai, Fisher Yu, Luc Van Gool

Published: 2023-03-07T18:28:41.000Z

## Abstract

Data-driven simulation has become a favorable way to train and test autonomous driving algorithms. The idea of replacing the actual environment with a learned simulator has also been explored in model-based reinforcement learning in the context of world models. In this work, we show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving, and based on TrafficBots we obtain a world model tailored for the planning module of autonomous vehicles. Existing data-driven traffic simulators are lacking configurability and scalability. To generate configurable behaviors, for each agent we introduce a destination as navigational information, and a time-invariant latent personality that specifies the behavioral style. To improve the scalability, we present a new scheme of positional encoding for angles, allowing all agents to share the same vectorized context and the use of an architecture based on dot-product attention. As a result, we can simulate all traffic participants seen in dense urban scenarios. Experiments on the Waymo open motion dataset show TrafficBots can simulate realistic multi-agent behaviors and achieve good performance on the motion prediction task.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Traffic Simulation Realism on Waymo Open Motion Dataset (WOMD) 2025 challenge (test)](<https://www.sota2.com/research/sota/traffic-simulation-realism-on-waymo-open-motion-dataset-womd-2025-challenge-test.md>): Traffic Simulation Realism; Waymo Open Motion Dataset (WOMD) 2025 challenge (test); Kinematic Score: 0.4304.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.04116>)

[PDF](<https://arxiv.org/pdf/2303.04116.pdf>)