Awesome Autonomous Driving (2026 Refresh)

May 30, 2026 · View on GitHub

Maintainers - Daehyun Ji (Samsung Electronics), Vertical AI 2 Team, AI Center Members in Samsung Electronics

I am looking for a maintainer! Let me know (captainzone@gmail.com) if interested.

Contributing

Please feel free to open pull requests to add papers, codebases, datasets, benchmarks, and courses.

Table of Contents

Papers

Overall Surveys

  • Self-Driving Cars: A Survey [Paper]
    • Claudine Badue, Rânik Guidolini, Raphael Vivacqua Carneiro, Pedro Azevedo, Vinicius Brito Cardoso, Avelino Forechi, Luan Ferreira Reis Jesus, Rodrigo Ferreira Berriel, Thiago Meireles Paixão, Filipe Mutz, Thiago Oliveira-Santos, Alberto Ferreira De Souza
  • Planning and Decision-Making for Autonomous Vehicles [Paper]
    • Wilko Schwarting, Javier Alonso-Mora, Daniela Rus
  • A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles [Paper]
    • Brian Paden, Michal Čáp, Sze Zheng Yong, Dmitry Yershov, Emilio Frazzoli
  • A Survey for Foundation Models in Autonomous Driving [Paper]
    • Haoxiang Gao, Zhongruo Wang, Yaqian Li, Kaiwen Long, Ming Yang, Yiqing Shen
  • A Survey of World Models for Autonomous Driving [Paper]
    • Tuo Feng, Wenguan Wang, Yi Yang
  • Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis [Paper]
    • Mingyang Zhang, Haotian Wang, Yiduo Wang, et al.

Foundation Models, VLMs, LLMs, and World Models

  • DriveLM: Driving with Graph Visual Question Answering [Paper] [Code]
    • Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang Li
  • Planning-Oriented Autonomous Driving [Paper] [Code]
    • Tianyuan Hu, Li Chen, et al.
  • TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving [Paper] [Code]
    • Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger
  • GAIA-1: A Generative World Model for Autonomous Driving [Paper]
    • Wayve
  • DriveTransformer / DriveGPT-style driving-language works
    • This area is moving quickly; keep an eye on VLM- and MLLM-based driving papers from CVPR, ICCV, ECCV, CoRL, and NeurIPS AD workshops.
  • World Models for Autonomous Driving: An Initial Survey [Paper]
    • Chenhan Jiang, et al.

Classification / Representation Learning

  • ImageNet Classification with Deep Convolutional Neural Networks [Paper]
    • Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
  • Very Deep Convolutional Networks for Large-Scale Image Recognition [Paper]
    • Karen Simonyan, Andrew Zisserman
  • Going Deeper with Convolutions [Paper]
    • Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich
  • Deep Residual Learning for Image Recognition [Paper]
    • Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
  • Densely Connected Convolutional Networks [Paper]
    • Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [Paper]
    • Alexey Dosovitskiy, et al.
  • A ConvNet for the 2020s [Paper]
    • Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie

2D Object Detection

  • Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation [Paper]
    • Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik
  • Fast R-CNN [Paper]
    • Ross Girshick
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [Paper]
    • Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
  • You Only Look Once: Unified, Real-Time Object Detection [Paper]
    • Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
  • SSD: Single Shot MultiBox Detector [Paper]
    • Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg
  • End-to-End Object Detection with Transformers [Paper]
    • Nicolas Carion, et al.
  • DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection [Paper]
    • Hao Zhang, et al.

3D Object Detection and BEV Perception

  • VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection [Paper]
    • Yin Zhou, Oncel Tuzel
  • PointPillars: Fast Encoders for Object Detection from Point Clouds [Paper]
    • Alex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, Oscar Beijbom
  • SECOND: Sparsely Embedded Convolutional Detection [Paper]
    • Yan Yan, Yuxing Mao, Bo Li
  • CenterPoint: Tracking Objects as Points [Paper]
    • Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
  • DETR3D: 3D Object Detection from Multi-View Images via 3D-to-2D Queries [Paper]
    • Yue Wang, et al.
  • PETR: Position Embedding Transformation for Multi-View 3D Object Detection [Paper]
    • Yilun Liu, et al.
  • BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers [Paper] [Code]
    • Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Qiao Yu, Jifeng Dai
  • BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation [Paper] [Code]
    • Zhijian Liu, Haotian Tang, Alexander Amini, Hanrui Wang, Song Han
  • Occupancy and BEV methods from 2023-2025
    • See also occupancy and end-to-end sections below, because the field increasingly merges 3D detection, map perception, forecasting, and planning.

Object Tracking

  • Simple Online and Realtime Tracking [Paper]
    • Alex Bewley, et al.
  • Simple Online and Realtime Tracking with a Deep Association Metric [Paper]
    • Nicolai Wojke, Alex Bewley, Dietrich Paulus
  • AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics [Paper] [Code]
    • Xinshuo Weng, Jianren Wang, David Held, Kris Kitani
  • CenterTrack: Tracking Objects as Points [Paper]
    • Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

Semantic Segmentation

  • Fully Convolutional Networks for Semantic Segmentation [Paper]
    • Jonathan Long, Evan Shelhamer, Trevor Darrell
  • Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs [Paper]
    • Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille
  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [Paper]
    • Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille
  • Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [Paper]
    • Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam
  • Pyramid Scene Parsing Network [Paper]
    • Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
  • SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers [Paper]
    • Enze Xie, et al.
  • Masked-attention Mask Transformer for Universal Image Segmentation [Paper]
    • Bowen Cheng, et al.

Depth Estimation

  • Unsupervised Monocular Depth Estimation with Left-Right Consistency [Paper] [Code]
    • Clement Godard, Oisin Mac Aodha, Gabriel J. Brostow
  • Digging into Self-Supervised Monocular Depth Estimation [Paper]
    • Clément Godard, Oisin Mac Aodha, Michael Firman, Gabriel J. Brostow
  • PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation [Paper]
    • Vitor Guizilini, et al.
  • DORN: Deep Ordinal Regression Network for Monocular Depth Estimation [Paper]
    • Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Dacheng Tao
  • Depth Anything [Paper] [Code]
    • Lihe Yang, et al.
  • Depth Anything V2 [Paper] [Code]
    • Lihe Yang, et al.

Occupancy Prediction and Scene Representation

  • SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving [Paper] [Code]
    • Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu
  • Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [Paper]
    • Yiming Ge, et al.
  • TPVFormer: Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction [Paper]
    • Yiming Huang, et al.
  • Occupancy Network / occupancy-based scene modeling papers (2023-2025)
    • This is now a core subfield linking perception, forecasting, and world modeling.

Localization and Mapping

  • Visual SLAM Algorithms: A Survey from 2010 to 2016 [Paper]
    • Takafumi Taketomi, Hideaki Uchiyama, Sei Ikeda
  • Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age [Paper]
    • César Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, Jose Neira, Ian Reid, John J. Leonard
  • LOAM: Lidar Odometry and Mapping in Real-time [Paper]
    • Ji Zhang, Sanjiv Singh
  • LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping [Paper] [Code]
    • Tianyue Shan, Brendan Englot, et al.
  • ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multi-Map SLAM [Paper] [Code]
    • Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez, José M. M. Montiel, Juan D. Tardós
  • FAST-LIO2: Fast Direct LiDAR-Inertial Odometry [Paper] [Code]
    • Wei Xu, et al.

Visual Odometry

  • Review of Visual Odometry: Types, Approaches, Challenges, and Applications [Paper]
    • Mohammad O. A. Aqel, Mohammad H. Marhaban, M. Iqbal Saripan, Napsiah Bt. Ismail
  • ORB-SLAM: A Versatile and Accurate Monocular SLAM System [Paper]
    • Raúl Mur-Artal, J. M. M. Montiel, Juan D. Tardós
  • DF-VO: What Should Be Learnt for Visual Odometry? [Paper]
    • Zhaoyang Lv, et al.
  • DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras [Paper] [Code]
    • Zachary Teed, Jia Deng

Lane Detection and HD Map Learning

  • Towards End-to-End Lane Detection: An Instance Segmentation Approach [Paper]
    • Davy Neven, Bert De Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool
  • Ultra Fast Structure-Aware Deep Lane Detection [Paper]
    • Zequn Qin, et al.
  • LaneATT: Robust Multi-Lane Detection from Stereo or Monocular Input [Paper] [Code]
    • Lucas Tabelini, Rodrigo Berriel, et al.
  • CLRNet: Cross Layer Refinement Network for Lane Detection [Paper] [Code]
    • Tianheng Cheng, et al.
  • MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction [Paper] [Code]
    • Bencheng Liao, et al.
  • StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction [Paper]
    • Jiahao He, et al.

Motion Forecasting and Behavior Prediction

  • VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation [Paper]
    • Li Liang, et al.
  • LaneGCN: Motion Forecasting with Lane Graph Convolutions [Paper]
    • Ming Liang, Bin Yang, Rui Hu, Yun Chen, Raquel Urtasun
  • MTR: Motion Transformer for Motion Prediction [Paper]
    • Shaoshuai Shi, et al.
  • Wayformer: Motion Forecasting via Simple and Efficient Attention Networks [Paper]
    • Yixiao Wei, et al.
  • Scene Transformer: A Unified Architecture for Predicting Multiple Agent Trajectories [Paper]
    • Junru Gu, et al.

Decision Making

  • Planning and Decision-Making for Autonomous Vehicles [Paper]
    • Wilko Schwarting, Javier Alonso-Mora, Daniela Rus
  • Perception, Planning, Control, and Coordination for Autonomous Vehicles [Paper]
    • R. K. Satzoda, Mohan M. Trivedi
  • A Behavioral Planning Framework for Autonomous Driving [Paper]
    • Junqing Wei, Jarrod M. Snider, Tianyu Gu, John M. Dolan, Bakhtiar Litkouhi
  • Towards a Functional System Architecture for Automated Vehicles [Paper]
    • Simon Ulbrich, Andreas Reschka, Jens Rieken, Susanne Ernst, Gerrit Bagschik, Frank Dierkes, Marcus Nolte, Markus Maurer

Planning

  • Optimal Trajectory Generation for Dynamic Street Scenarios in a Frenet Frame [Paper]
    • Moritz Werling, Julius Ziegler, Sören Kammel, Sebastian Thrun
  • Path Planning for Autonomous Vehicles in Unknown Semi-Structured Environments [Paper]
    • Dmitri Dolgov, et al.
  • Trajectory Planning for Bertha — A Local, Continuous Method [Paper]
    • Julius Ziegler, Philipp Bender, Thao Dang, Christoph Stiller
  • Real-Time Motion Planning Methods for Autonomous On-Road Driving: State-of-the-Art and Future Research Directions [Paper]
    • Christos Katrakazas, Mohammed Quddus, Wen-Hua Chen, Lipika Deka
  • A Review of Motion Planning Techniques for Automated Vehicles [Paper]
    • David González, Joshué Pérez, Vicente Milanés, Fawzi Nashashibi
  • Towards Learning-Based Planning: The nuPlan Benchmark for Real-World Autonomous Driving [Paper]
    • Holger Caesar, et al.

Control

  • Stanley: The Robot that Won the DARPA Grand Challenge [Paper]
    • Sebastian Thrun, et al.
  • Automatic Steering Methods for Autonomous Automobile Path Tracking [Paper]
    • Jarrod M. Snider
  • A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles [Paper]
    • Brian Paden, Michal Čáp, Sze Zheng Yong, Dmitry Yershov, Emilio Frazzoli

End-to-End Driving

  • Learning by Cheating [Paper] [Code]
    • Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl
  • TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving [Paper] [Code]
    • Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger
  • NEAT: Neural Attention Fields for End-to-End Autonomous Driving [Paper] [Code]
    • Bernhard Jaeger, et al.
  • TCP: Trajectory-guided Control Prediction for End-to-End Autonomous Driving [Paper] [Code]
    • Haotian Tang, et al.
  • Planning-Oriented Autonomous Driving [Paper] [Code]
    • Tianyuan Hu, Li Chen, et al.
  • DriveLM: Driving with Graph Visual Question Answering [Paper] [Code]
    • Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang Li

Reinforcement Learning in Autonomous Driving

  • Playing for Data: Ground Truth from Computer Games [Paper]
    • Stephan R. Richter, Vibhav Vineet, Stefan Roth, Vladlen Koltun
  • Deep Reinforcement Learning for Autonomous Driving: A Survey [Paper]
    • Kissan Tiwari, Bikash K. Dey, et al.
  • Benchmarking Reinforcement Learning for Autonomous Driving in CARLA
    • Search terms: RL + CARLA + CoRL / NeurIPS / ICRA / IV for the latest policy-learning papers.

Datasets and Benchmarks

  • KITTI Vision Benchmark Suite [Website]
    • Classical benchmark for stereo, optical flow, visual odometry, 3D object detection, and tracking.
  • Cityscapes [Website]
    • Urban scene understanding benchmark with fine semantic annotations.
  • Mapillary Vistas [Website]
    • Large-scale, geographically diverse street-scene parsing dataset.
  • BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning [Paper] [Website]
    • Large-scale multi-task driving dataset.
  • Waymo Open Dataset [Website] [About]
    • Large-scale perception, motion, scenario generation, and end-to-end driving benchmark ecosystem.
  • nuScenes [Website]
    • Multi-sensor dataset for detection, tracking, segmentation, prediction, and map-related tasks.
  • nuPlan [Website] [Paper]
    • Closed-loop planning benchmark with simulation and scenario-based evaluation.
  • Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting [Website] [Paper]
    • Covers sensor, lidar, motion forecasting, map-change detection, and related tasks.
  • Waymo Open Motion Dataset / Waymax ecosystem [Waymax] [Docs]
    • Useful for behavior prediction, sim agents, scenario generation, and closed-loop evaluation.
  • ApolloScape [Website]
    • Includes scene parsing, car instance, lane segmentation, self-localization, and trajectory tasks.
  • SYNTHIA [Website]
    • Synthetic dataset for semantic segmentation and related perception tasks.
  • Oxford RobotCar Dataset [Website]
    • Long-term autonomy dataset across weather, season, and lighting changes.
  • Oxford Radar RobotCar Dataset [Website]
    • Adds radar and odometry for robust localization and adverse-condition research.
  • KAIST Urban Dataset / MulRan-style Korean localization datasets
    • Keep Korean-road and Korean-traffic-specific resources in this section where possible.

Courses

  • CS231n: Convolutional Neural Networks for Visual Recognition [Website]
  • Self-Driving Cars Specialization (University of Toronto / Coursera) [Website]
  • Introduction to Self-Driving Cars [Website]
  • Practical Deep Learning for Coders [Website]
  • Probabilistic Robotics and SLAM related graduate lectures
    • Search with: SLAM / visual localization / motion planning / multi-agent forecasting lecture series.

Books

  • Deep Learning — Ian Goodfellow, Yoshua Bengio, Aaron Courville [Book]
  • Probabilistic Robotics — Sebastian Thrun, Wolfram Burgard, Dieter Fox [Book]
  • Planning Algorithms — Steven M. LaValle [Book]
  • Principles of Robot Motion: Theory, Algorithms, and Implementations — Howie Choset, et al. [Book]
  • Computer Vision: Algorithms and Applications — Richard Szeliski [Book]

Videos

  • Computer Vision Foundation (CVF) Open Access / YouTube [Channel]
  • ROSCon [Channel]
  • Autonomous Driving talks from Waymo Research / NVIDIA / Motional / CARLA Summit
  • Classical deep learning lectures
    • Andrew Ng, Geoffrey Hinton, Yann LeCun, Yoshua Bengio

Software

ROS and Autonomous Driving Stacks

Frameworks and Toolboxes

Simulation and Evaluation

Conference and Workshop Channels

  • CVPR [Website]
  • ICCV [Website]
  • ECCV [Website]
  • NeurIPS [Website]
  • ICRA [Website]
  • IROS [Website]
  • IEEE Intelligent Vehicles Symposium (IV) [Website]
  • CoRL (Conference on Robot Learning) [Website]
  • Workshop keywords to watch
    • autonomous driving, embodied AI, world models, behavior prediction, foundation models, simulation, safety validation

Maintenance Notes

  • Prefer full paper titles over abbreviations when adding new entries.
  • Prefer official project pages, official code repositories, and arXiv / OpenAccess links.
  • Mark deprecated toolchains clearly (for example, Torch7, Theano, Caffe2) instead of deleting history.
  • For 2026+, the most active update zones are:
    • foundation models / VLM / LLM driving
    • world models and scenario generation
    • occupancy and BEV scene representation
    • end-to-end driving
    • motion forecasting and sim agents
    • planning benchmarks and closed-loop evaluation

Suggested Next Cleanup for This Repository

  • Add tags such as Classic, Recommended, 2024+, Code, Benchmark, and Survey.
  • Split the README into papers.md, datasets.md, software.md, and courses.md if it becomes too long.
  • Add a small section for Korean-road / Korean-traffic-light / Korean-map resources.
  • Add benchmark tables for 3D detection, forecasting, planning, and end-to-end driving.