Language Conditioned Traffic Generation

Shuhan Tan, Boris Ivanovic, Xinshuo Weng, Marco Pavone, Philipp Kraehenbuehl
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2714-2752, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-tan23a, title = {Language Conditioned Traffic Generation}, author = {Tan, Shuhan and Ivanovic, Boris and Weng, Xinshuo and Pavone, Marco and Kraehenbuehl, Philipp}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2714--2752}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/tan23a/tan23a.pdf}, url = {https://proceedings.mlr.press/v229/tan23a.html}, 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.} }
Endnote
%0 Conference Paper %T Language Conditioned Traffic Generation %A Shuhan Tan %A Boris Ivanovic %A Xinshuo Weng %A Marco Pavone %A Philipp Kraehenbuehl %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-tan23a %I PMLR %P 2714--2752 %U https://proceedings.mlr.press/v229/tan23a.html %V 229 %X 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.
APA
Tan, S., Ivanovic, B., Weng, X., Pavone, M. & Kraehenbuehl, P.. (2023). Language Conditioned Traffic Generation. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2714-2752 Available from https://proceedings.mlr.press/v229/tan23a.html.

Related Material