paper-with-me

Papers

DriveFuture: Future-Aware Latent World Models for Autonomous Driving

2026-05-10 · Yufeng Hong, Xiaotian Zhou, Yingyan Li, Xiangpo Zhou, Lin Liu, Yadan Luo, Shaoqing Xu, Lei Yang, Ziying Song arxiv

Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat future latent states as prediction targets or auxiliary signals, rather than directly conditioning trajectory planning. This can entangle current and future features in latent space. In this work, we propose DriveFuture, a future-aware latent world modeling framework for autonomous driving that explicitly learns planning-oriented foresight by conditioning the current latent state modeling process on future world states. Specifically, during training, the model first predicts future latent world states from the current latent state and ego action, and then refines the prediction against the ground-truth future latent state via cross-attention. The resulting future-aware latent serves as an explicit condition for a diffusion-based trajectory planner. During inference, DriveFuture conditions on the predicted future latent state instead of the ground-truth future state. DriveFuture achieves SOTA performance on the public NAVSIM benchmarks, reaching \textbf{55.5} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}, \textbf{89.9} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navtest}}}, and \textbf{90.7} PDMS on NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}, respectively. These results suggest that the key to latent world modeling lies not merely in simulating future states, but more importantly in conditioning current decision-making on future states. Notably, as of April 2026, DriveFuture ranks \textbf{1st} on the \href{https://huggingface.co/spaces/AGC2025/e2e-driving-navhard}{NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}} leaderboard and achieves SOTA performance on \href{https://huggingface.co/spaces/AGC2024-P/e2e-driving-navtest}{NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}}.

📄 PDF Abstract BibTeX arXiv:2605.09701

Code (0)

등록된 구현이 없습니다.

Tasks

Trajectory PlanningAutonomous Driving

Similar Papers 제목 키워드 기반

IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving

2026-05-29 · Chenghao Zhang, Timin Li, Dongmei Li arxiv

End-to-end autonomous driving has emerged as a compelling paradigm for learning planning directly from sensor observations, while recent world-model-based approaches further enrich this paradigm by enabling explicit reas…

Autonomous Driving

Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

2026-03-25 · Linbo Wang, Yupeng Zheng, Qiang Chen, Shiwei Li 외 arxiv

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-base…

Trajectory PlanningAutonomous Driving

GeoWorldAD: Geometry World Action Model for Autonomous Driving

2026-07-20 · Songyan Zhang, Jinyuan Tian, Hanbing Li, Daqi Liu 외 arxiv

Autonomous driving requires both safe and efficient planning decisions in dynamic 3D environments. Although recent Vision/Video-Action models learn policies directly from visual observations and scale well with advances …

Collision AvoidanceTrajectory PlanningAutonomous Driving

LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model

2026-05-21 · Xiaodong Mei, Diankun Zhang, Hongwei Xie, Guang Chen 외 arxiv

Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene un…

Representation LearningImage ReconstructionScene UnderstandingAutonomous Driving

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

2025-07-01 · Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang 외

End-to-end autonomous driving directly generates planning trajectories from raw sensor data, yet it typically relies on costly perception supervision to extract scene information. A critical research challenge arises: co…

Autonomous DrivingNavSimSelf-Supervised Learning