method · first seen 5 Oct 2026
end-to-end autonomous driving
Also: E2E driving, end-to-end driving, end-to-end navigation
Driving policies that map sensor inputs directly to vehicle control or trajectories in one learned model.
End-to-end autonomous driving trains a single model to map camera or LiDAR input directly to trajectories or controls, replacing hand-built perception, prediction and planning modules. The sources are a steady stream of incremental work rather than a new idea. They include query-based cost learning over reachable trajectories, sparse alternatives to dense BEV grids (BEVCast, LOWP), JEPA-style and latent world-action models, risk-sensitive candidate ranking, cooperative intent sharing, and benchmarks for in-context decisions. OpenDriveLab released code studying whether visual foundation models help planning, and one team adapted openpilot for NVIDIA's AlpaSim closed-loop challenge. The active subtopics are world models, VLA planners and closed-loop evaluation.
The overall paradigm has been a mainstream research direction since UniAD and earlier imitation-learning work, so this rise mostly reflects normal paper volume. The subthreads worth watching are latent world models and closed-loop evaluation in neural-reconstructed scenes.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 163 on 14 Nov 2026 · 18 mentions in 28 days · 16 independent groups · papers → code · first seen 6 weeks ago · acceleration +1.22
Earliest sources
- Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous DrivingPapers · 5 Oct 2026 · Minkyoung Cho, Zewei Zhou, Wenhao Ding, Shuhan Tan, Boyi Li, Yuxiao Chen, Yan Wa…
- Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End DrivingPapers · 6 Oct 2026 · Ahmed Abouelazm, Rupert Polley, Qingyuan Zhang, Yin Wu, Philip Schörner, Carl E…
- OpenDriveLab/ViRACode · 6 Oct 2026 · OpenDriveLab · 34 stars
- Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?Papers · 7 Oct 2026 · Zihao Zhang, Haochen Tian, Tianyu Li, Changhui Jing, Jingliang He, Naisheng Ye,…
- PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous DrivingPapers · 8 Oct 2026 · Jinchang Xu, Hongda Yu, Fengwei Dong, Wenhui Huang, Xi Wei, Yongzhi Liu, Sunan Z…
- SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous DrivingPapers · 8 Oct 2026 · Chengjun Zhang, Yuhao Zhang, Jie Yang, Mohamad Sawan
Latest sources
- WTR-Drive: World-Task Decomposition with Structured Risk Supervision for End-to-End DrivingPapers · 16 Nov 2026 · Haoyu Xing, Shaobing Ding, Guanglei Zhao, Guanhua Zhao, Nawu Peng, Mingyang Hou
- Lao Siji: Adapting openpilot to Closed-Loop End-to-End Driving in Neural ReconstructionPapers · 15 Nov 2026 · Chengzhi Gao, Yongzhi Liu, Jinchang Xu, Weichao Zhuang, Guodong Yin
- ActWorld-JEPA: Action-Conditioned JEPA World Models Meet Latent Planning for End-to-End Autonomous DrivingPapers · 12 Nov 2026 · Ziying Song, Shengkai Zhang, Caiyan Jia, Lei Yang, Lin Liu, Yuchen Liu, Ziyang L…
- CARE-Drive: Coupled Alternating Refinement for Ego-trajectoriesPapers · 11 Nov 2026 · Xiao Ma, Yijun Chen, Zhiquan Hu, Jicheng Zhao, Ran Ji, Yuming Li, Chuang Dai
- RiSE-Drive: Risk-Sensitive Long-Horizon Candidate Evaluation for End-to-End Autonomous DrivingPapers · 10 Nov 2026 · Yu Zhao, Hongyi Duan, Ming Yin, Hongyuan Zhang, Fan Yang, Hongzhi Wang, Xiubo Li…
- DeRep: Learning Depth Representations for End-to-End Navigation in Cluttered EnvironmentsPapers · 10 Nov 2026 · Hanyu Jin, Kenji Shimada
- Route-Time Conflict Maps for Cooperative End-to-End Autonomous DrivingPapers · 10 Nov 2026 · Haohua Que, Mingkai Liu, Tianle Zhu, Zhipeng Bao, Yiping Li, Handong Yao
- Latent-WAM++: Shaping World and Action Representations for End-to-End Autonomous DrivingPapers · 7 Nov 2026 · Yichen Zhang, Yupeng Zheng, Linbo Wang, Pengxuan Yang, Zebin Xing, Junli Wang, S…
- Look Only Where You Plan for Real-Time End-to-End Urban DrivingPapers · 6 Nov 2026 · Haohua Que, Tianle Zhu, Qianyi Wu, Zhipeng Bao, Handong Yao
- BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous DrivingPapers · 5 Nov 2026 · Qiren Wang, Mingyu Guo, Zixuan Wang, Weisong Shi
- PlanContext: Benchmarking In-Context Driving Decision-MakingPapers · 2 Nov 2026 · Ruikai Li, Naiyu Gao, Hao Shan, Yizhe Fan, Yanhao Wu, Han Jiang, Yilong Ren, Zhe…
- Scaling Action-Free Video Latent Prediction for Transferable Representations in End-to-End Autonomous DrivingPapers · 2 Nov 2026 · Xingtai Gui, Xubin Zhou, Yucheng Zhou, Dongqian Guo, Jiahao Gong, Feiyang Tan, J…