干货来啦！端到端自动驾驶文章汇总

xiaocheng

综述汇总

Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A SurveyEnd-to-end Autonomous Driving: Challenges and Frontiers开源仓库：https://github.com/opendilab/awesome-end-to-end-autonomous-driving#a-Overview-of-End-to-End-Driving-Method开源仓库：https://github.com/Pranav-chib/Recent-Advancements-in-End-to-End-Autonomous-Driving-using-Deep-Learning

基于可解释性

基于Attention

Planning-oriented Autonomous Driving Best Paper [CVPR2023]Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling [ICLR2023]Scaling Self-Supervised End-to-End Driving with Multi-View Attention Learning [arxiv2023]TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving [TPAMI2022]Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer[CoRL2022]PlanT: Explainable Planning Transformers via Object-Level Representations[CoRL2022]Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [CVPR2021]NEAT: Neural Attention Fields for End-to-End Autonomous Driving [ICCV2021]

Semantic representation and Auxiliary output

Learning from All Vehicles [CVPR2022]TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving [TPAMI2022]ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning [ECCV2022]Hidden Biases of End-to-End Driving Models[arXiv2023]Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer[CoRL2022]Learning Situational Driving[CVPR2020]

基于模仿学习

Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving. [CVPR2023]Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling [ICLR2023]Hidden Biases of End-to-End Driving Models [arXiv2023]Scaling Self-Supervised End-to-End Driving with Multi-View Attention Learning [arxiv2023]Learning from All Vehicles [CVPR2022]PlanT: Explainable Planning Transformers via Object-Level Representations [CoRL2022]Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [CVPR2021]Learning by Watching [CVPR2021]End-to-End Urban Driving by Imitating a Reinforcement Learning Coach [ICCV2021]Learning by Cheating [CoRL2020]SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning [[CoRL2020]]Urban Driving with Conditional Imitation Learning [ICRA2020]Multimodal End-to-End Autonomous Driving [TITS2020]Learning to Drive from Simulation without Real World Labels [ICRA2019]

基于行为克隆

TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving [TPAMI2022]Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline [NeurIPS2022]KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients [ECCV2022]Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining [ECCV2022]NEAT: Neural Attention Fields for End-to-End Autonomous Driving [ICCV2021]Learning Situational Driving [CVPR2020]Exploring the Limitations of Behavior Cloning for Autonomous Driving [ICCV2019]

基于强化学习

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization [ICLR2022]End-to-End Urban Driving by Imitating a Reinforcement Learning Coach [ICCV2021]Learning To Drive From a World on Rails [ICCV2021]End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit Affordances [CVPR2020]Learning to drive in a day [ICRA2019]

基于多任务学习

Planning-oriented Autonomous Driving Best Paper [CVPR2023]ReasonNet: End-to-End Driving with Temporal and Global Reasoning [CVPR2023]Coaching a Teachable Student [CVPR2023]Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving. [CVPR2023]Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer [CoRL2022]SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning [[CoRL2020]]Urban Driving with Conditional Imitation Learning [ICRA2020]

基于知识蒸馏

Learning from All Vehicles [CVPR2022]End-to-End Urban Driving by Imitating a Reinforcement Learning Coach [ICCV2021]Learning To Drive From a World on Rails [ICCV2021]Learning by Cheating [CoRL2020]SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning [[CoRL2020]]

cengjili

好的，根据您的要求，作为汽车工程师的我为您整理了关于端到端自动驾驶的相关资料。

近期，端到端自动驾驶技术利用深度学习取得了显著进展。其涵盖了视觉感知、路径规划、决策控制等多个环节，对自动驾驶系统的实现起到了关键作用。在此附上两个开源仓库链接，第一个提供了对该技术的综述和最新进展的全面概述，第二个则涉及到具体的实践和技术细节。这些内容为您全面了解并深入研究端到端自动驾驶技术提供了宝贵资源。希望这些资料能对您有所助益。

随风1

根据您的需求，我将以汽车工程师的专业视角来回复有关端到端自动驾驶的文章汇总及综述。

尊敬的读者，感谢您的关注。近期，端到端自动驾驶技术取得显著进展，特别是在深度学习领域的应用。此技术涵盖了自动驾驶的全过程，从感知、决策到控制。以下是相关开源仓库的链接，涵盖了端到端驾驶方法的综述及挑战探讨。

开源仓库一：opendilab/awesome-end-to-end-autonomous-driving。这个仓库提供了关于端到端驾驶的全面概述及最新研究进展。
开源仓库二：Pra所提供的资源则可能包含关于端到端自动驾驶的挑战和前沿技术探讨。

以上资源为研究者及爱好者提供了深入了解端到端自动驾驶技术的平台。随着技术的不断进步，自动驾驶的未来充满无限可能。

若您对此领域有更多问题或需求，欢迎进一步交流。