FocalAD: Local Motion Planning for End-to-End Autonomous Driving

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Bin, Zhang, Boao, Lu, Jiayi, Feng, Xinjie, Shang, Jiachen, Cao, Rui, Zheng, Mengchao, Wang, Chuanye, Yang, Shichun, Cao, Yaoguang, Song, Ziying
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915999377260544
author Sun, Bin
Zhang, Boao
Lu, Jiayi
Feng, Xinjie
Shang, Jiachen
Cao, Rui
Zheng, Mengchao
Wang, Chuanye
Yang, Shichun
Cao, Yaoguang
Song, Ziying
author_facet Sun, Bin
Zhang, Boao
Lu, Jiayi
Feng, Xinjie
Shang, Jiachen
Cao, Rui
Zheng, Mengchao
Wang, Chuanye
Yang, Shichun
Cao, Yaoguang
Song, Ziying
contents In end-to-end autonomous driving,the motion prediction plays a pivotal role in ego-vehicle planning. However, existing methods often rely on globally aggregated motion features, ignoring the fact that planning decisions are primarily influenced by a small number of locally interacting agents. Failing to attend to these critical local interactions can obscure potential risks and undermine planning reliability. In this work, we propose FocalAD, a novel end-to-end autonomous driving framework that focuses on critical local neighbors and refines planning by enhancing local motion representations. Specifically, FocalAD comprises two core modules: the Ego-Local-Agents Interactor (ELAI) and the Focal-Local-Agents Loss (FLA Loss). ELAI conducts a graph-based ego-centric interaction representation that captures motion dynamics with local neighbors to enhance both ego planning and agent motion queries. FLA Loss increases the weights of decision-critical neighboring agents, guiding the model to prioritize those more relevant to planning. Extensive experiments show that FocalAD outperforms existing state-of-the-art methods on the open-loop nuScenes datasets and closed-loop Bench2Drive benchmark. Notably, on the robustness-focused Adv-nuScenes dataset, FocalAD achieves even greater improvements, reducing the average colilision rate by 41.9% compared to DiffusionDrive and by 15.6% compared to SparseDrive.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11419
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FocalAD: Local Motion Planning for End-to-End Autonomous Driving
Sun, Bin
Zhang, Boao
Lu, Jiayi
Feng, Xinjie
Shang, Jiachen
Cao, Rui
Zheng, Mengchao
Wang, Chuanye
Yang, Shichun
Cao, Yaoguang
Song, Ziying
Artificial Intelligence
Robotics
In end-to-end autonomous driving,the motion prediction plays a pivotal role in ego-vehicle planning. However, existing methods often rely on globally aggregated motion features, ignoring the fact that planning decisions are primarily influenced by a small number of locally interacting agents. Failing to attend to these critical local interactions can obscure potential risks and undermine planning reliability. In this work, we propose FocalAD, a novel end-to-end autonomous driving framework that focuses on critical local neighbors and refines planning by enhancing local motion representations. Specifically, FocalAD comprises two core modules: the Ego-Local-Agents Interactor (ELAI) and the Focal-Local-Agents Loss (FLA Loss). ELAI conducts a graph-based ego-centric interaction representation that captures motion dynamics with local neighbors to enhance both ego planning and agent motion queries. FLA Loss increases the weights of decision-critical neighboring agents, guiding the model to prioritize those more relevant to planning. Extensive experiments show that FocalAD outperforms existing state-of-the-art methods on the open-loop nuScenes datasets and closed-loop Bench2Drive benchmark. Notably, on the robustness-focused Adv-nuScenes dataset, FocalAD achieves even greater improvements, reducing the average colilision rate by 41.9% compared to DiffusionDrive and by 15.6% compared to SparseDrive.
title FocalAD: Local Motion Planning for End-to-End Autonomous Driving
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2506.11419