Language Conditioned Traffic Generation

Shuhan Tan, Boris Ivanovic, Xinshuo Weng, Marco Pavone, Philipp Kraehenbuehl

Keywords: Self-driving, Content generation, Large language model

TL;DR: We propose a language-conditioned traffic scenario generation model powered by LLM.

Abstract: Simulation forms the backbone of modern self-driving development. Simulators help develop, test, and improve driving systems without putting humans, vehicles, or their environment at risk. However, simulators face a major challenge: They rely on realistic, scalable, yet interesting content. While recent advances in rendering and scene reconstruction make great strides in creating static scene assets, modeling their layout, dynamics, and behaviors remains challenging. In this work, we turn to language as a source of supervision for dynamic traffic scene generation. Our model, LCTGen, combines a large language model with a transformer-based decoder architecture that selects likely map locations from a dataset of maps, and produces an initial traffic distribution, as well as the dynamics of each vehicle. LCTGen outperforms prior work in both unconditional and conditional traffic scene generation in terms of realism and fidelity.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Website: https://ariostgx.github.io/lctgen/

Code: https://github.com/Ariostgx/lctgen

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/language-conditioned-traffic-generation/code)