Asynchronous Large Language Model Enhanced Planner for Autonomous Driving

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Yuan, Ding, Zi-han, Wang, Ziqin, Wang, Yan, Zhang, Lijun, Liu, Si
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911965411016704
author Chen, Yuan
Ding, Zi-han
Wang, Ziqin
Wang, Yan
Zhang, Lijun
Liu, Si
author_facet Chen, Yuan
Ding, Zi-han
Wang, Ziqin
Wang, Yan
Zhang, Lijun
Liu, Si
contents Despite real-time planners exhibiting remarkable performance in autonomous driving, the growing exploration of Large Language Models (LLMs) has opened avenues for enhancing the interpretability and controllability of motion planning. Nevertheless, LLM-based planners continue to encounter significant challenges, including elevated resource consumption and extended inference times, which pose substantial obstacles to practical deployment. In light of these challenges, we introduce AsyncDriver, a new asynchronous LLM-enhanced closed-loop framework designed to leverage scene-associated instruction features produced by LLM to guide real-time planners in making precise and controllable trajectory predictions. On one hand, our method highlights the prowess of LLMs in comprehending and reasoning with vectorized scene data and a series of routing instructions, demonstrating its effective assistance to real-time planners. On the other hand, the proposed framework decouples the inference processes of the LLM and real-time planners. By capitalizing on the asynchronous nature of their inference frequencies, our approach have successfully reduced the computational cost introduced by LLM, while maintaining comparable performance. Experiments show that our approach achieves superior closed-loop evaluation performance on nuPlan's challenging scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14556
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asynchronous Large Language Model Enhanced Planner for Autonomous Driving
Chen, Yuan
Ding, Zi-han
Wang, Ziqin
Wang, Yan
Zhang, Lijun
Liu, Si
Robotics
Computer Vision and Pattern Recognition
Despite real-time planners exhibiting remarkable performance in autonomous driving, the growing exploration of Large Language Models (LLMs) has opened avenues for enhancing the interpretability and controllability of motion planning. Nevertheless, LLM-based planners continue to encounter significant challenges, including elevated resource consumption and extended inference times, which pose substantial obstacles to practical deployment. In light of these challenges, we introduce AsyncDriver, a new asynchronous LLM-enhanced closed-loop framework designed to leverage scene-associated instruction features produced by LLM to guide real-time planners in making precise and controllable trajectory predictions. On one hand, our method highlights the prowess of LLMs in comprehending and reasoning with vectorized scene data and a series of routing instructions, demonstrating its effective assistance to real-time planners. On the other hand, the proposed framework decouples the inference processes of the LLM and real-time planners. By capitalizing on the asynchronous nature of their inference frequencies, our approach have successfully reduced the computational cost introduced by LLM, while maintaining comparable performance. Experiments show that our approach achieves superior closed-loop evaluation performance on nuPlan's challenging scenarios.
title Asynchronous Large Language Model Enhanced Planner for Autonomous Driving
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.14556