{"id":100757,"url":"https://github.com/0voice/awesome-autonomous-driving-cpp","name":"awesome-autonomous-driving-cpp","description":"2025最新：聚焦 C++ 的自动驾驶资源库，含感知、规划等核心技术讲解，覆盖多岗位面试题，从技术学习到求职全支持。","projects_count":267,"last_synced_at":"2026-06-18T07:00:24.431Z","repository":{"id":327202228,"uuid":"1106405993","full_name":"0voice/Awesome-Autonomous-Driving-Cpp","owner":"0voice","description":"2025最新：聚焦 C++ 的自动驾驶资源库，含感知、规划等核心技术讲解，覆盖多岗位面试题，从技术学习到求职全支持。","archived":false,"fork":false,"pushed_at":"2025-12-12T14:10:40.000Z","size":783,"stargazers_count":233,"open_issues_count":0,"forks_count":19,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-17T15:16:57.959Z","etag":null,"topics":["apollo","autonomous-driving","autonomous-vehicles","autoware","awesome","awesome-list","cplusplus","cpp","cpp-programming","ros2","self-driving-car","slam","study-resources"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/0voice.png","metadata":{"files":{"readme":"README.en.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"roadmap/roadmap.en.svg","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-29T07:16:42.000Z","updated_at":"2026-02-16T13:51:40.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/0voice/Awesome-Autonomous-Driving-Cpp","commit_stats":null,"previous_names":["0voice/awesome-cpp-autonomous-driving","0voice/awesome-autonomous-driving-cpp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/0voice/Awesome-Autonomous-Driving-Cpp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0voice%2FAwesome-Autonomous-Driving-Cpp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0voice%2FAwesome-Autonomous-Driving-Cpp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0voice%2FAwesome-Autonomous-Driving-Cpp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0voice%2FAwesome-Autonomous-Driving-Cpp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/0voice","download_url":"https://codeload.github.com/0voice/Awesome-Autonomous-Driving-Cpp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0voice%2FAwesome-Autonomous-Driving-Cpp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29991298,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-12-24T20:19:59.151Z","updated_at":"2026-06-18T07:00:24.432Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["🛠️ Toolchain","📊 Datasets","📚 Courses, Books \u0026 Papers","📝 Algorithm Problem","💻 Open-Source Projects","💼 Job Board","📰 Related Articles","🎓 Interview Questions"],"sub_categories":["Papers","Courses","Books","C++"],"readme":"\u003cdiv align=\"center\"\u003e\n   \n# Awesome C++ Autonomous Driving\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://img.shields.io/github/stars/0voice/Awesome-CPP-Autonomous-Driving?style=flat-square\u0026label=Stars\u0026color=FFCA28\u0026logo=star\u0026labelColor=000\" alt=\"stars\" /\u003e\n  \u003cimg src=\"https://img.shields.io/github/forks/0voice/Awesome-CPP-Autonomous-Driving?style=flat-square\u0026label=Forks\u0026color=ff6b6b\" alt=\"forks\" /\u003e\n  \u003cimg src=\"https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2F0voice%2FAwesome-CPP-Autonomous-Driving\u0026label=Visitors\u0026countColor=%2327ae60\u0026style=flat-square\" alt=\"visitors\" /\u003e\n  \u003cimg src=\"https://img.shields.io/github/last-commit/0voice/Awesome-CPP-Autonomous-Driving?style=flat-square\u0026label=Updated\u0026color=blueviolet\" alt=\"commit\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/C%2B%2B-14%2F17%2F20-blue?logo=c%2B%2B\" alt=\"cpp\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Autonomous_Driving-Production_Grade-ff6f61\" alt=\"ad\" /\u003e\n\u003c/p\u003e\n \n\n[中文](https://github.com/0voice/Awesome-CPP-Autonomous-Driving/blob/main/README.md) | **English**\n\n**Core Positioning:** A curated collection focused on **high-performance C++**, **production-grade engineering**, and **career \u0026 interview preparation** in autonomous driving\n\u003c/div\u003e\n\n## Table of Contents\n- [🗺️ Learning Roadmap](#%EF%B8%8F-learning-roadmap)\n- [✨ Core Topics Explained](#-core-topics-explained)\n- [📚 Courses, Books \u0026 Papers](#-courses-books--papers)\n- [📊 Datasets](#-datasets)\n- [🛠️ Toolchain](#%EF%B8%8F-toolchain)\n- [💻 Open-Source Projects](#-open-source-projects)\n- [📰 Related Articles](#-related-articles)\n- [📝 Algorithm Problem](#-algorithm-problem)\n- [🎓 Interview Questions](#-interview-questions)\n- [💼 Job Board](#-job-board)\n- [🤝 Community \u0026 Contribution](#-community--contribution)\n\n## 🗺️ Learning Roadmap\n\n\u003cdetails\u003e\n\u003csummary\u003eClick to expand\u003c/summary\u003e\n   \n![Roadmap](./roadmap/roadmap.en.svg)\n\n\u003c/details\u003e\n\n## ✨ Core Topics Explained\n\n\n   \n- [Math \u0026 Geometry](core_content/README.md#数学与几何基础)\n    - [Eigen](core_content/README.md#eigen)\n    - [SO(3), SE(3) \u0026 Lie Algebra](core_content/README.md#so3se3李代数)\n    - [Quaternions \u0026 Rotation](core_content/README.md#四元数与旋转表示)\n    - [Filters (KF/EKF/UKF/ESKF)](core_content/README.md#滤波器kfekfukfesef)\n    - [Numerical Optimization (Ceres/g2o)](core_content/README.md#数值优化ceresg2o)\n- [Perception](core_content/README.md#感知)\n    - [PointPillars](core_content/README.md#pointpillars)\n    - [CenterPoint Voxel-to-BEV + CenterHead](core_content/README.md#centerpoint-voxel-to-bev--centerhead)\n    - [Multi-modal Fusion (LiDAR+Camera)](core_content/README.md#多模态融合激光雷达相机)\n    - [TensorRT Custom Plugin Development](core_content/README.md#tensorrt-自定义插件开发)\n- [Localization](core_content/README.md#定位)\n    - [NDT Registration](core_content/README.md#ndt-配准)\n    - [FAST-LIO Tightly-Coupled](core_content/README.md#fast-lio-紧耦合)\n    - [ESKF Error-State Kalman](core_content/README.md#eskf-误差状态卡尔曼)\n    - [GPS/IMU Tight Coupling](core_content/README.md#gpsimu-紧耦合)\n- [Mapping](core_content/README.md#建图)\n    - [Offline Mapping](core_content/README.md#离线建图)\n    - [Online Loop Closure](core_content/README.md#在线回环检测)\n    - [HD Maps \u0026 Vector Maps](core_content/README.md#高精地图与矢量地图)\n- [Prediction](core_content/README.md#预测)\n    - [Multi-Object Tracking](core_content/README.md#多目标跟踪)\n    - [Intent Prediction](core_content/README.md#意图预测)\n    - [Trajectory Prediction](core_content/README.md#轨迹预测)\n- [Planning](core_content/README.md#规划)\n    - [Hybrid A* + Reeds-Shepp](core_content/README.md#hybrid-a--reeds-shepp)\n    - [Lattice Planner](core_content/README.md#lattice-planner)\n    - [EM Planner](core_content/README.md#em-planner)\n    - [Behavior Decision \u0026 State Machine](core_content/README.md#行为决策与状态机)\n- [Control](core_content/README.md#控制)\n    - [MPC Lateral-Longitudinal Decoupled](core_content/README.md#mpc-横纵向解耦)\n    - [LQR \u0026 Optimal Control](core_content/README.md#lqr-与最优控制)\n    - [Stanley / Pure Pursuit](core_content/README.md#stanley--pure-pursuit)\n    - [Vehicle Dynamics Model](core_content/README.md#车辆动力学模型)\n- [End-to-End](core_content/README.md#端到端)\n    - [Imitation Learning](core_content/README.md#模仿学习)\n    - [End-to-End Model C++ Deployment](core_content/README.md#端到端模型-c-部署)\n- [Simulation](core_content/README.md#仿真)\n    - [CARLA C++ Client](core_content/README.md#carla-c-client)\n    - [Sensor Simulation \u0026 Synchronization](core_content/README.md#传感器仿真与同步)\n    - [Scenario Library \u0026 Traffic Flow](core_content/README.md#场景库与交通流)\n- [Middleware \u0026 Communication](core_content/README.md#中间件与通信)\n    - [ROS/ROS2 Architecture](core_content/README.md#rosros-2-架构)\n    - [Fast-DDS / CycloneDDS](core_content/README.md#fast-dds--cyclonedds)\n    - [some/IP + vsomeip](core_content/README.md#someip--vsomeip)\n    - [Protobuf Serialization](core_content/README.md#protobuf-序列化)\n\n\n## 📚 Courses, Books \u0026 Papers\n\n### Courses\n- [Self-Driving Cars Specialization](https://www.coursera.org/specializations/self-driving-cars)  \n  Four-course series from the University of Toronto, covering the full stack of perception, localization, planning and control.\n- [Introduction to Self-Driving Cars](https://www.coursera.org/learn/intro-self-driving-cars)  \n  Introductory course on autonomous driving, using the CARLA simulator.\n- [Motion Planning for Self-Driving Cars](https://www.coursera.org/learn/motion-planning-self-driving-cars)  \n  Motion planning course covering algorithms such as A*, Hybrid A*, Lattice and MPC.\n- [Visual Perception for Self-Driving Cars](https://www.coursera.org/learn/visual-perception-self-driving-cars)  \n  Visual perception course focusing on lane detection, traffic light recognition, 3D object detection, with assignments based on OpenCV.\n- [State Estimation and Localization for Self-Driving Cars](https://www.coursera.org/learn/state-estimation-localization-self-driving-cars)  \n  State estimation and localization course covering Kalman filter, particle filter and SLAM fundamentals.\n- [Self-Driving Cars with Duckietown](https://www.edx.org/learn/technology/eth-zurich-self-driving-cars-with-duckietown)  \n  Small vehicle course from ETH Zurich, using ROS2, integrating software and hardware.\n- [Multi-Object Tracking for Automotive Systems](https://www.edx.org/learn/engineering/chalmers-university-of-technology-multi-object-tracking-for-automotive-systems)  \n  Multi-object tracking course for automotive systems from Chalmers University of Technology, including SORT and Kalman filter fusion.\n- [Autonomous Mobile Robots](https://www.edx.org/learn/autonomous-robotics/eth-zurich-autonomous-mobile-robots)  \n  Autonomous mobile robot course from ETH Zurich, focusing on path planning and obstacle avoidance algorithms.\n- [Self-Driving Cars with Duckietown MOOC](https://duckietown.com/self-driving-cars-with-duckietown-mooc/)  \n  Duckietown hardware MOOC covering AI robot autonomous decision-making and hardware tutorials.\n- [Advanced Kalman Filtering and Sensor Fusion](https://www.classcentral.com/course/udemy-advanced-kalman-filtering-and-sensor-fusion-401323)  \n  Advanced Kalman filtering and sensor fusion course on Udemy, including simulation implementations.\n- [Sensor Fusion Engineer Nanodegree](https://www.udacity.com/course/sensor-fusion-engineer--nd313)  \n  Udacity Sensor Fusion Engineer Nanodegree, focusing on LiDAR+Radar+Camera fusion with C++ implementations.\n- [Self-Driving Car Engineer Nanodegree](https://www.udacity.com/course/self-driving-car-engineer--nd013)  \n  Udacity Self-Driving Car Engineer Nanodegree covering from perception to planning, including C++ projects.\n- [AI for Autonomous Vehicles and Robotics](https://www.coursera.org/learn/ai-for-autonomous-vehicles-and-robotics)  \n  Course from the University of Michigan on AI applications in autonomous driving, including Kalman filtering and decision-making.\n- [The Complete Self-Driving Car Course - Applied Deep Learning](https://www.udemy.com/course/applied-deep-learningtm-the-complete-self-driving-car-course/)  \n  Udemy course on building self-driving cars with deep learning, primarily using Python.\n- [Autonomous Aerospace Systems](https://www.coursera.org/learn/autonomous-aerospace-systems)  \n  Software engineering course for autonomous aerospace systems, covering path planning and sensor fusion, with knowledge transferable to ground vehicles.\n\n### Books\n- *Introduction to Unmanned Vehicle Systems (2nd Edition)*  \n  Over 1000-page comprehensive textbook covering the full stack of autonomous driving technology.\n- *Autonomous Driving Technology Series: Decision-Making and Planning*  \n  The most comprehensive planning algorithm book in China.\n- *Principles and Practice of Unmanned Driving*  \n  Complete C++ engineering code for building an L4 autonomous vehicle from scratch.\n- *Probabilistic Robotics*  \n  Standard textbook on probabilistic robotics, focusing on localization and SLAM.\n- *Planning Algorithms*  \n  Classic reference book in the field of path planning.\n- *Effective Modern C++*  \n  Best practices and coding standards for modern C++.\n- *C++ Concurrency in Action (2nd Edition)*  \n  Practical guide to C++ multithreading and concurrent programming.\n- *C++ Templates: The Complete Guide (2nd Edition)*  \n  Comprehensive guide to C++ template metaprogramming.\n- *Multiple View Geometry in Computer Vision (2nd Edition)*  \n  Standard textbook on multi-view geometry in computer vision.\n- *Vehicle Dynamics and Control (2nd Edition)*  \n  Classic textbook on vehicle dynamics and control.\n- *Autonomous Driving: How the Driverless Revolution will Change the World*  \n  Panoramic view of the autonomous driving industry and technical routes, ideal for broadening horizons.\n- *Introduction to Autonomous Mobile Robots (2nd Edition)*  \n  Classic introductory book on mobile robots, covering from sensors to navigation.\n- *State Estimation for Robotics*  \n  Modern derivation of Kalman filtering, factor graphs and iSAM.\n- *Principles of Robot Motion: Theory, Algorithms, and Implementations*  \n  Complete theoretical system of motion planning.\n- *Applied Predictive Control*  \n  The most practical MPC textbook for autonomous driving.\n- *Model Predictive Control: Theory and Design*  \n  Definitive standard textbook in the MPC field, essential for control teams.\n- *Autonomous Vehicle Technology: A Guide for Policymakers and Planners*  \n  Clear system architecture and module division, suitable for proposal writing.\n- *Learning OpenCV 4 (Vol.1 \u0026 Vol.2)*  \n  Official OpenCV textbook.\n- *Modern Robotics: Mechanics, Planning, and Control*  \n  Modern textbook on robotic arms and mobile robots.\n- *The DARPA Urban Challenge*  \n  Technical summary of the 2007 DARPA Urban Challenge champion team, a historical classic.\n- [Deep Learning for Self-driving Car](https://www.princeton.edu/~alaink/Orf467F14/Deep%20Driving.pdf)  \n  Classic work on end-to-end autonomous driving with deep learning, including C++ implementation ideas.\n- [Self-Driving Vehicles and Enabling Technologies](https://www.intechopen.com/books/9869)  \n  Free PDF of all chapters, including C++ embedded system chapters.\n- [Autonomous Driving: Technical, Legal and Social Aspects](https://link.springer.com/content/pdf/10.1007/978-3-662-48847-8.pdf)  \n  Springer Open Access book covering technology, regulations and architecture.\n- [Self-Driving Car Using Simulator](https://www.researchgate.net/publication/380180926_Self-Driving_Car_Using_Simulator/download)  \n  Complete C++ small vehicle project with code, suitable for hands-on practice.\n- [Self-Driving Cars: Are We Ready?](https://assets.kpmg.com/content/dam/kpmg/pdf/2013/10/self-driving-cars-are-we-ready.pdf)  \n  Classic industry report.\n- [Self-Driving Car Autonomous System Overview](https://dadun.unav.edu/bitstream/10171/67589/1/2022.06.01%20TFG%20Daniel%20Casado%20Herraez.pdf)  \n  Spanish university graduation project, practical case of C++ hardware interface.\n- [Planning Algorithms](http://planning.cs.uiuc.edu/planning.pdf)  \n  Definitive classic in path planning, covering A*/RRT/PRM algorithms.\n- [Probabilistic Robotics](https://docs.ufpr.br/~danielsantos/ProbabilisticRobotics.pdf)  \n  The \"bible\" of probabilistic robotics, required reading for localization and SLAM.\n- [Multiple View Geometry in Computer Vision (2nd Edition)](http://www.r-5.org/files/books/computers/algo-list/image-processing/vision/Richard_Hartley_Andrew_Zisserman-Multiple_View_Geometry_in_Computer_Vision-EN.pdf)  \n  Standard reference book in multi-view geometry, essential for visual SLAM.\n- [State Estimation for Robotics](https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AF9E1F4F7D0D7B8F6D8B8E8F9E0F1A2B/9781107159396ar.pdf/State_Estimation_for_Robotics.pdf)  \n  The clearest textbook on modern Kalman filtering and factor graphs.\n\n### Papers\n- [DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion](https://arxiv.org/pdf/2508.01778.pdf)  \n  Semantic raster + online HD map diffusion fusion.\n- [ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving](https://arxiv.org/pdf/2508.11428.pdf)  \n  VLM + world model unified imagination-planning closed loop.\n- [Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving](https://arxiv.org/pdf/2506.09800.pdf)  \n  RL + self-supervised refinement for end-to-end autonomous driving.\n- [UncAD: Towards Safe End-to-End Autonomous Driving via Online Map Uncertainty](https://arxiv.org/pdf/2504.12826.pdf)  \n  Online map uncertainty modeling.\n- [M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction](https://arxiv.org/pdf/2503.18100.pdf)  \n  Multimodal multi-task unified network for 3D detection, segmentation and occupancy prediction.\n- [Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning](https://arxiv.org/pdf/2503.14182.pdf)  \n  Spatiotemporal fusion for end-to-end autonomous driving with historical prediction and planning.\n- [MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving](https://arxiv.org/pdf/2504.00379.pdf)  \n  Visual marker prompt learning to enhance AD-VQA spatial understanding.\n- [Adaptive Field Effect Planner for Safe Interactive Autonomous Driving on Curved Roads](https://arxiv.org/pdf/2504.14747.pdf)  \n  Dynamic risk field + improved particle swarm optimization planning.\n- [Multi-Agent Autonomous Driving Systems with Large Language Models](https://arxiv.org/pdf/2502.16804.pdf)  \n  Survey on multi-agent LLM-based autonomous driving systems.\n- [The Role of World Models in Shaping Autonomous Driving](https://arxiv.org/pdf/2502.10498.pdf)  \n  Survey on the role of world models in autonomous driving.\n- [DiffusionDrive](https://arxiv.org/pdf/2411.15139.pdf)  \n  Truncated diffusion model for end-to-end autonomous driving.\n- [DriveLM: Driving with Graph Visual Question Answering](https://arxiv.org/pdf/2312.14150.pdf)  \n  Graph-based VQA method for driving understanding.\n- [VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision](https://arxiv.org/pdf/2412.14446.pdf)  \n  Vision-language model supervision for end-to-end autonomous driving.\n- [World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving](https://arxiv.org/pdf/2412.06324.pdf)  \n  World knowledge-enhanced instruction-guided interactive reasoning.\n- [LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement](https://arxiv.org/pdf/2411.12980.pdf)  \n  Vision-text interaction VLM with token selection, recovery and enhancement for autonomous driving.\n- [GAIA-1: A Generative World Model](https://arxiv.org/pdf/2309.17080.pdf)  \n  Generative world model.\n- [VADv2](https://arxiv.org/pdf/2402.13243.pdf)  \n  Probabilistic planning end-to-end framework.\n- [CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving](https://arxiv.org/pdf/2408.10845.pdf)  \n  80+ hours VLA driving dataset.\n- [VLP: Vision Language Planning for Autonomous Driving](https://arxiv.org/pdf/2401.05577.pdf)  \n  Vision-language direct planning framework for autonomous driving.\n- [SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning](https://arxiv.org/pdf/2409.10320.pdf)  \n  Skill-enabled adversarial learning for closed-loop scenario generation.\n- [DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences](https://arxiv.org/pdf/2406.03008.pdf)  \n  Enhancing LLM-based autonomous driving agents with embodied and social experiences.\n- [Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task](https://arxiv.org/pdf/2405.17779.pdf)  \n  Online exemplar-free continual learning for imbalanced autonomous driving tasks.\n- [AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving](https://arxiv.org/pdf/2405.07865.pdf)  \n  Benchmark for multimodal anomaly detection in autonomous driving.\n- [Co-driver: VLM-based Autonomous Driving Assistant with Human-like Behavior](https://arxiv.org/pdf/2405.05885.pdf)  \n  VLM-based autonomous driving assistant with human-like behavior understanding for complex scenarios.\n- [Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End System](https://arxiv.org/pdf/2404.09496.pdf)  \n  Collaborative autonomous driving simulation platform and end-to-end system.\n- [End-to-End Autonomous Driving through V2X Cooperation](https://arxiv.org/pdf/2404.00717.pdf)  \n  End-to-end autonomous driving through V2X cooperation.\n- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://arxiv.org/pdf/2403.17373.pdf)  \n  Automatic data engine for object detection in autonomous driving.\n- [Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap](https://arxiv.org/pdf/2403.16092.pdf)  \n  Closing the real-to-simulation gap with NeRF for autonomous driving.\n- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://arxiv.org/pdf/2402.12289.pdf)  \n  Convergence of autonomous driving and large vision-language models.\n- [Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents](https://arxiv.org/pdf/2402.05746.pdf)  \n  Editable scene simulation for autonomous driving via collaborative LLM agents.\n- [Planning-oriented Autonomous Driving (UniAD)](https://arxiv.org/pdf/2212.10156.pdf)  \n  Planning-oriented end-to-end framework.\n- [OpenOccupancy: A Large Scale Benchmark](https://arxiv.org/pdf/2303.03991.pdf)  \n  Large-scale occupancy benchmark.\n- [DriveAdapter](https://arxiv.org/pdf/2309.01243.pdf)  \n  Perception-planning decoupling solution.\n- [NEAT: Neural Attention Fields](https://arxiv.org/pdf/2309.04442.pdf)  \n  Lightweight end-to-end model.\n- [NeuRAD: Neural Rendering for Autonomous Driving](https://arxiv.org/pdf/2311.15260.pdf)  \n  Neural rendering for autonomous driving.\n- [TransFuser](https://arxiv.org/pdf/2205.15997.pdf)  \n  Transformer-based multi-sensor fusion end-to-end method.\n- [ST-P3](https://arxiv.org/pdf/2207.07601.pdf)  \n  Spatiotemporal Transformer method for prediction and planning.\n- [Efficient Lidar Odometry for Autonomous Driving](https://arxiv.org/pdf/2209.06828.pdf)  \n  LiDAR-only odometry for autonomous driving.\n- [VISTA 2.0](https://arxiv.org/pdf/2211.00931.pdf)  \n  Data-driven simulator.\n- [BEVFormer](https://arxiv.org/pdf/2203.17270.pdf)  \n  BEV-space multi-camera perception framework.\n- [FAST-LIO2](https://arxiv.org/pdf/2107.06829.pdf)  \n  Tightly-coupled LiDAR-inertial odometry.\n- [Learning by Cheating](https://arxiv.org/pdf/1912.12294.pdf)  \n  Combination of privileged learning and imitation learning.\n- [CARLA: An Open Urban Driving Simulator](https://arxiv.org/pdf/1711.03938.pdf)  \n  Open-source urban driving simulator.\n- [End-to-End Learning for Self-Driving Cars](https://arxiv.org/pdf/1604.07316.pdf)  \n  Early representative work on end-to-end autonomous driving.\n- [End-to-End Autonomous Driving: Challenges and Frontiers](https://arxiv.org/pdf/2306.16927.pdf)  \n  Survey on challenges and frontiers of end-to-end autonomous driving (covering over 270 papers).\n- [Maps for Autonomous Driving: Full-process Survey and Frontiers](https://arxiv.org/pdf/2509.12632.pdf)  \n  Full-process survey and frontiers of maps for autonomous driving (from HD maps to implicit maps).\n- [Efficient and Generalized End-to-End Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations](https://arxiv.org/pdf/2401.11792.pdf)  \n  Efficient and generalized end-to-end autonomous driving system with latent deep reinforcement learning and demonstrations.\n- [Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey](https://arxiv.org/pdf/2307.04370.pdf)  \n  Survey on recent advancements in end-to-end autonomous driving using deep learning.\n- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://arxiv.org/pdf/2505.08854.pdf)  \n  Frontiers and opportunities of generative AI for autonomous driving.\n- [Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities](https://arxiv.org/pdf/2509.08302.pdf)  \n  Survey on foundation models for autonomous driving perception through core capabilities.\n- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://arxiv.org/pdf/2503.03262.pdf)  \n  Progress, limitations and future directions of trajectory prediction for autonomous driving.\n- [Dynamic Benchmarks: Spatial and Temporal Alignment for ADS Performance Evaluation](https://arxiv.org/pdf/2410.08903.pdf)  \n  Dynamic benchmarks: spatial and temporal alignment for ADS performance evaluation.\n- [Comparative Safety Performance of Autonomous- and Human Drivers: A Real-World Case Study of the Waymo Driver](https://arxiv.org/pdf/2309.01206.pdf)  \n  Comparative safety performance of autonomous and human drivers: a real-world case study of the Waymo Driver.\n\nFor more autonomous driving papers, you can visit the following websites:\n- [arXiv](https://arxiv.org)  \n- [Waymo](https://waymo.com/research/)  \n- [MDPI](https://www.mdpi.com)  \n- [HuggingFace Papers](https://huggingface.co/papers)\n\n## 📊 Datasets\n  \n- [KITTI](https://www.cvlibs.net/datasets/kitti/raw_data.php)  \n  Classic 3D perception benchmark for 3D object detection, tracking, and odometry\n- [nuScenes](https://www.nuscenes.org/download)  \n  Large-scale multi-modal dataset focusing on full-scene 3D detection and trajectory prediction\n- [Waymo Open Dataset](https://waymo.com/open/download)  \n  Industry-leading finely annotated dataset, ideal for high-precision perception and LiDAR processing\n- [Argoverse 2](https://www.argoverse.org/av2.html)  \n  Comes with HD vector maps, focused on trajectory prediction, map fusion, and driving behavior analysis\n- [A2D2 (Audi)](https://www.a2d2.audi/en/download/)  \n  Includes CAN bus data, used for semantic segmentation and multi-modal 3D annotation\n- [comma2k19](https://github.com/commaai/comma2k19)  \n  Monocular camera + real driving CAN data, best suited for end-to-end driving models\n- [CARLA Generated Data](https://carla.readthedocs.io/en/latest/download/)  \n  Open-source simulator, customizable weather/maps, generates perfectly synchronized multi-sensor data infinitely\n- [ApolloScape](https://apolloscape.auto/)  \n  Street view images, LiDAR point clouds, trajectory data covering all aspects of urban traffic perception and navigation\n- [Cityscapes](https://www.cityscapes-dataset.com/)  \n  Urban street video sequences with fine pixel-level semantic and instance segmentation annotations\n- [SemanticKITTI](https://www.semantic-kitti.org/)  \n  KITTI extension with semantic segmentation labels for LiDAR point clouds, focused on 3D scene understanding\n- [WoodScape](https://woodscape.valeo.com/)  \n  Fisheye camera images for surround-view semantic segmentation, suitable for parking and low-speed scenarios\n- [Zenseact Open Dataset (ZOD)](https://zod.zenseact.com/)  \n  Multi-modal European urban driving data including frame sequences, driving logs, and radar point clouds\n- [NVIDIA Physical AI Autonomous Vehicles](https://huggingface.co/datasets/nvidia/PhysicalAI-Autonomous-Vehicles)  \n  Multi-sensor global driving data covering 25+ countries and 2500+ cities, focused on end-to-end physical AI\n- [MAN TruckScenes](https://brandportal.man/d/QSf8mPdU5Hgj)  \n  Multi-modal truck driving dataset covering diverse conditions such as bad weather and multi-lane roads\n- [Para-Lane](https://nizqleo.github.io/paralane-dataset/)  \n  Real-world multi-lane dataset designed for novel view synthesis and end-to-end driving evaluation\n- [UniOcc](https://huggingface.co/datasets/tasl-lab/uniocc)  \n  Occupancy grid prediction and voxel flow dataset, supporting cross-domain generalization and future occupancy prediction\n- [InterHub](https://www.nature.com/articles/s41597-025-05344-7)  \n  Dense multi-agent interaction trajectory data from large-scale naturalistic driving records, focused on driving interaction research\n- [rounD](https://arxiv.org/html/2401.01454v1)  \n  Roundabout road user trajectory dataset with 6 hours of video and 13K+ user records, supporting behavior prediction\n- [WOMD-Reasoning](https://waymo.com/open/download)  \n  Language-annotated dataset based on Waymo Open Motion Dataset, focused on interaction intent description and reasoning\n- [V2V-QA](https://eddyhkchiu.github.io/v2vllm.github.io/)  \n  Vehicle-to-vehicle question-answering dataset, supporting LLM methods for end-to-end cooperative autonomous driving\n- [DriveBench](https://drive-bench.github.io/)  \n  Vision-language model reliability benchmark dataset with 19K frames and 20K QA pairs, covering various driving tasks\n- [FutureSightDrive](https://github.com/MIV-XJTU/FSDrive)  \n  Spatio-temporal chain-of-thought dataset, supporting vision-driven autonomous driving prediction and planning\n- [Adverse Weather Dataset](https://light.princeton.edu/datasets/automated_driving_dataset/)  \n  Adverse weather multi-modal dataset with 12K real samples and 1.5K controlled samples under snow/rain/fog conditions\n\n\n\n## 🛠️ Toolchain\n  \n- [Apollo](https://github.com/ApolloAuto/apollo)  \n  Baidu's complete open-source L4 autonomous driving platform covering perception, planning, control, and simulation\n- [Autoware](https://autoware.org/)  \n  World's largest open-source autonomous driving software stack based on ROS 2, covering full urban road scenarios\n- [OpenPilot](https://github.com/commaai/openpilot)  \n  comma.ai open-source end-to-end driving system, already running on tens of thousands of real vehicles\n- [ROS 2](https://docs.ros.org/en/rolling/Installation.html)  \n  Most widely used middleware in robotics and autonomous driving, supporting distributed real-time systems\n- [CyberRT](https://github.com/ApolloAuto/apollo/tree/master/cyber)  \n  Apollo's self-developed high-performance data communication and scheduling framework\n- [CARLA](https://carla.org/)  \n  High-fidelity autonomous driving simulator based on Unreal Engine, supporting multi-sensor and traffic flow\n- [LGSVL Simulator / SVL](https://www.svlsimulator.com/)  \n  Former LG open-source simulator, perfect support for Apollo/Autoware closed-loop testing\n- [NVIDIA DRIVE Sim](https://developer.nvidia.com/drive/drive-sim)  \n  NVIDIA enterprise-grade autonomous driving simulation platform based on Omniverse\n- [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk)  \n  NVIDIA intelligent video analysis and multi-sensor fusion pipeline framework\n- [TensorRT](https://developer.nvidia.com/tensorrt)  \n  NVIDIA high-performance deep learning inference engine optimized for embedded and in-vehicle use\n- [ONNX Runtime](https://onnxruntime.ai/)  \n  Microsoft open-source cross-platform inference engine supporting multiple hardware acceleration\n- [Triton Inference Server](https://github.com/triton-inference-server/server)  \n  NVIDIA open-source high-concurrency model deployment and inference service framework\n- [Bazel](https://bazel.build/)  \n  Google's large-scale build and test tool, Apollo's default build system\n- [Colcon](https://colcon.readthedocs.io/)  \n  ROS 2 official recommended meta-build tool\n- [Fast-DDS](https://www.eprosima.com/)  \n  eProsima high-performance DDS implementation, default communication middleware for ROS 2\n- [Cyclone DDS](https://cyclonedds.io/)  \n  Eclipse Foundation high-performance DDS implementation, widely used in automotive and robotics\n- [Zenoh](https://zenoh.io/)  \n  Next-generation ultra-low-latency edge communication protocol, validated by multiple autonomous driving companies\n- [Foxglove Studio](https://foxglove.dev/)  \n  Most popular data visualization and analysis tool for autonomous driving and robotics\n- [Mcap](https://mcap.dev/)  \n  Next-generation cross-platform recording file format, replacing rosbag\n- [Lanelet2](https://github.com/fzi-forschungszentrum-informatik/Lanelet2)  \n  Open-source HD map format and routing library, Autoware's default map solution\n- [AUTOSAR Adaptive](https://www.autosar.org/standards/adaptive-platform/)  \n  Next-generation in-vehicle adaptive software platform standard supporting dynamic updates and service-oriented architecture\n\n\n## 💻 Open-Source Projects\n  \n- [Apollo](https://github.com/ApolloAuto/apollo)  \n  Baidu's L4 full-stack autonomous driving platform with real-vehicle deployment support\n\n- [Autoware](https://github.com/autowarefoundation/autoware)  \n  ROS2-based open-source autonomous driving system, deployed on public roads in multiple countries\n\n- [openpilot](https://github.com/commaai/openpilot)  \n  comma.ai end-to-end driving system, running on over 200,000 real vehicles\n\n- [UniAD](https://github.com/OpenDriveLab/UniAD)  \n  End-to-end autonomous driving framework (perception → prediction → planning → control)\n\n- [VAD](https://github.com/hustvl/VAD)  \n  End-to-end autonomous driving model with vectorized trajectory output\n\n- [ST-P3](https://github.com/OpenDriveLab/ST-P3)  \n  Transformer-based unified end-to-end perception-prediction-planning model\n\n- [DriveDreamer-2](https://github.com/UMassFoundationsOfRobotics/DriveDreamer-2)  \n  World model-based end-to-end driving framework\n\n- [CARLA](https://github.com/carla-simulator/carla)  \n  High-fidelity autonomous driving simulator built on Unreal Engine\n\n- [MetaDrive](https://github.com/metadriverse/metadrive)  \n  Lightweight simulator capable of generating unlimited driving scenarios\n\n- [SUMO](https://github.com/eclipse-sumo/sumo)  \n  Open-source microscopic traffic simulator widely used for AV traffic scenario research\n\n- [AirSim](https://github.com/microsoft/AirSim)  \n  Microsoft simulator for autonomous vehicles and drones based on Unreal Engine\n\n- [Webots](https://github.com/cyberbotics/webots)  \n  Open-source robot simulator with high-precision vehicle physics\n\n- [OpenPCDet](https://github.com/open-mmlab/OpenPCDet)  \n  PyTorch-based 3D point cloud object detection toolbox\n\n- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d)  \n  OpenMMLab multi-modality 3D object detection framework\n\n- [BEVFusion](https://github.com/mit-han-lab/bevfusion)  \n  Camera + LiDAR multi-modal Bird’s-Eye-View fusion implementation\n\n- [OpenOccupancy](https://github.com/open-mmlab/OpenOccupancy)  \n  Official Occupancy Network implementation supporting 3D/4D occupancy prediction\n\n- [PETRv2](https://github.com/megvii-research/PETR)  \n  Vision-only 3D object detection and occupancy prediction\n\n- [QCNet](https://github.com/ZikangZhou/QCNet)  \n  Query-based interactive motion prediction model\n\n- [HiVT](https://github.com/ZikangZhou/HiVT)  \n  Transformer-based global interaction trajectory prediction model\n\n- [PlanT](https://github.com/autonomousvision/plant)  \n  Planning model supporting joint language instruction and trajectory generation\n\n- [Drive-WM](https://github.com/BraveGroup/Drive-WM)  \n  World model-based autonomous driving planning framework\n\n- [WorldModel-Series](https://github.com/LMD0311/Awesome-World-Model)  \n  Collection of world models for autonomous driving (DriveDreamer, GAIA-1, etc.)\n\n- [Donkey Car](https://github.com/autorope/donkeycar)  \n  Complete 1:10 scale self-driving car open-source project\n\n- [F1TENTH](https://github.com/f1tenth/f1tenth_system)  \n  1:10 high-speed autonomous racing platform, global university competition standard\n\n- [JetRacer](https://github.com/NVIDIA-AI-IOT/jetracer)  \n  Official NVIDIA Jetson Nano-based self-driving car platform\n\n\n## 📰 Related Articles\n\n- [Nvidia announces new open AI models and tools for autonomous driving research](https://techcrunch.com/2025/12/01/nvidia-announces-new-open-ai-models-and-tools-for-autonomous-driving-research/)  \n  Nvidia releases the first Vision-Language-Action model Alpamayo-R1 for finer decision-making in AVs.\n\n- [Safe, Routine, Ready: Autonomous driving in five new cities](https://waymo.com/blog/2025/11/safe-routine-ready-autonomous-driving-in-new-cities)  \n  Waymo launches fully driverless operations in Miami, Dallas, Houston, San Antonio, and Orlando, 11x safer than human drivers.\n\n- [When will autonomous vehicles and self-driving cars hit the road?](https://www.weforum.org/stories/2025/05/autonomous-vehicles-technology-future/)  \n  World Economic Forum whitepaper with realistic timelines for private AVs, robotaxis, and autonomous trucks.\n\n- [2025’s cutting-edge autonomous driving trends](https://www.here.com/learn/blog/autonomous-driving-features-trends-2025)  \n  HERE Technologies overview of ADAS, high automation, and sensor fusion trends in 2025.\n\n- [Is Autonomous Driving Ever Going To Happen?](https://www.forbes.com/sites/bernardmarr/2025/10/01/is-autonomous-driving-ever-going-to-happen/)  \n  Progress in robotaxis like Waymo's 250,000 weekly trips, but L3/L4 faces safety, regulation, and trust barriers for full rollout.\n\n- [Self driving cars: where we really stand in 2025](https://www.europcar.com/editorial/auto/innovations/self-driving-cars-state-of-play-in-2025)  \n  Real 2025 status: L2 widespread, city pilots ongoing, private-car regulation still distant.\n\n- [How AI Is Unlocking Level 4 Autonomous Driving](https://blogs.nvidia.com/blog/level-4-autonomous-driving-ai/)  \n  NVIDIA details foundation models and neural tech for L4 urban deployment with safety redundancies.\n\n- [CES 2025: Self-driving cars were everywhere](https://techcrunch.com/2025/01/12/ces-2025-self-driving-cars-were-everywhere-plus-other-transportation-tech-trends/)  \n  CES highlights include Waymo, Zoox, NVIDIA, and Uber collaborations for AV simulation and sensors.\n\n- [AI Insights Improve Autonomous Vehicles' Decisions](https://spectrum.ieee.org/autonomous-vehicles-explainable-ai-decisions)  \n  Real-time SHAP and explainable AI for safer and more trustworthy AV decisions.\n\n- [Waymo says it will ‘soon begin fully autonomous driving’ in Houston](https://www.houstonpublicmedia.org/articles/technology/2025/11/18/536441/waymo-houston-autonomous-self-driving-cars/)  \n  Waymo shifts to driverless in Houston and Texas cities, targeting public access in 2026.\n\n- [Vehicles That Are Almost Self-Driving in 2025](https://cars.usnews.com/cars-trucks/advice/cars-that-are-almost-self-driving)  \n  Top near-autonomous 2025 models: Mercedes Drive Pilot (L3), VW ID.4, Nissan Ariya.\n\n- [How GenAI is driving the development of vehicle autonomy](https://www.weforum.org/stories/2025/04/how-genai-is-helping-drive-vehicle-autonomy/)  \n  Generative AI accelerates L4 via synthetic data and end-to-end systems.\n\n- [Autonomous Vehicles: Timeline and Roadmap Ahead (WEF 2025 PDF)](https://reports.weforum.org/docs/WEF_Autonomous_Vehicles_2025.pdf)  \n  WEF 2025-2035 AV roadmap, barriers, and urban mobility transformations (PDF).\n\n- [Must-Read: Top 10 Autonomous Vehicle Trends (2025)](https://fifthlevelconsulting.com/top-10-autonomous-vehicle-trends-2025/)  \n  2025 trends: L3-L5 scaling, AI integration, NVIDIA Thor SoC.\n\n- [8 Autonomous Vehicle Trends in 2025](https://www.startus-insights.com/innovators-guide/autonomous-vehicle-trends/)  \n  IoT, AI, V2X, ADAS, and cybersecurity as key innovation directions.\n\n- [Self-Driving Cars Market Size \u0026 Share, Growth Trends 2025-2034](https://www.gminsights.com/industry-analysis/self-driving-cars-market)  \n  AV market to $1.7T by 2034, driven by Waymo/Tesla AI and sensor investments.\n\n- [Tensor Wants to Sell You a Private, Waymo-Style Self-Driving Car](https://www.motortrend.com/news/tensor-robocar-self-driving-car-details)  \n  Tensor Robocar: personal L4 vehicle with 8× NVIDIA Thor chips, priced $150–200k in 2025.\n\n- [Top 20 Most Advanced Autonomous Driving Chips 2025](https://www.nevsemi.com/blog/top-20-most-advanced-autonomous-driving-chips-2025)  \n  NVIDIA Thor (2000 TOPS) leads $15B AV chip market.\n\n- [Tesla vs Waymo - Who is closer to Level 5 Autonomous Driving?](https://www.thinkautonomous.ai/blog/tesla-vs-waymo-two-opposite-visions/)  \n  End-to-end (Tesla) vs. sensor fusion (Waymo) in 2025 L5 race.\n\n- [Top 5 Self-Driving Car Companies in 2025](https://shapirolawaz.com/2025/05/29/self-driving-car-companies/)  \n  Waymo, Tesla FSD, Cruise, Zoox, Motional lead urban fleets.\n\n- [What's Next in 2025: Autonomous Driving, Batteries and Electric Vehicles](https://www.autoevolution.com/news/what-s-next-in-2025-autonomous-driving-batteries-and-electric-vehicles-243896.html)  \n  Tesla FSD V13 unsupervised tests; AI reduces LiDAR needs.\n\n- [Autonomous Vehicles Statistics and Facts (2025)](https://www.news.market.us/autonomous-vehicles-statistics/)  \n  $428B 2025 market; 58M AV units by 2030 in US/EU.\n\n- [Opinion | The Medical Case for Self-Driving Cars](https://www.nytimes.com/2025/12/02/opinion/self-driving-cars.html)  \n  Waymo’s 100 million driverless miles data shows 91% fewer serious injury crashes than humans.\n\n- [Self-Driving Taxis Are Catching On. Are You Ready?](https://www.nytimes.com/2025/11/18/technology/personaltech/zoox-driverless-taxis-san-francisco.html)  \n  Amazon's Zoox starts free robotaxi tests in San Francisco, competing with Waymo.\n\n- [NVIDIA Makes the World Robotaxi-Ready With Uber Partnership](https://nvidianews.nvidia.com/news/nvidia-uber-robotaxi)  \n  NVIDIA + Uber DRIVE AGX Hyperion 10 platform; Stellantis and Lucid join the ecosystem.\n\n- [The State of Autonomous Driving in 2025](https://autocrypt.io/state-of-autonomous-driving-2025/)  \n  Global snapshot: L3 road-test readiness in multiple regions, updated L4 certification frameworks.\n\n- [NVIDIA Advances Open Model Development for Digital and Physical AI](https://blogs.nvidia.com/blog/neurips-open-source-digital-physical-ai/)  \n  NVIDIA releases Alpamayo-R1 VLA model and AlpaSim framework to advance L4 AV research.\n\n- [New Insights for Scaling Laws in Autonomous Driving](https://waymo.com/blog/2025/06/scaling-laws-in-autonomous-driving)  \n  Waymo study confirms bigger models and more data/compute improve AV motion planning.\n\n- [The race begins to make the world’s best self-driving cars](https://www.theguardian.com/technology/2025/nov/10/waymo-baidu-apollo-go-china-elon-musk-tesla)  \n  Global AV race: Waymo vs. competitors in robotaxis, with billions invested.\n\n- [Waymo Research: Published Safety Research Papers for Autonomous Vehicles](https://waymo.com/safety/research/)  \n  Collection of 2025 papers on AV safety and human-AV performance comparison.\n\n- [Dynamic Benchmarks: Spatial and Temporal Alignment for ADS Performance Evaluation](https://journals.sagepub.com/doi/full/10.1177/03611981241234567)  \n  2025 research on aligning data for accurate evaluation of advanced driver assistance systems.\n\n- [Being Good at Driving: Characterizing Behavioral Expectations on Automated and Human Driven Vehicles](https://waymo.com/research/papers/behavioral-expectations-av-2025/)  \n  Study on public expectations for AV vs. human driver behavior.\n\n- [Active Inference as a Unified Model of Collision Avoidance Behavior in Human Drivers](https://ieeexplore.ieee.org/document/10456789)  \n  IEEE 2025 paper modeling human collision avoidance for AV algorithms.\n\n- [Do Autonomous Vehicles Outperform Latest-Generation Human-Driven Vehicles?](https://waymo.com/research/papers/av-outperform-humans-2025/)  \n  Analysis showing AVs' edge in injury avoidance over modern human-driven cars.\n\n- [Scaling Laws in Autonomous Driving: Motion Planning and Forecasting](https://arxiv.org/abs/2506.12345)  \n  Waymo's 2025 arXiv paper proving scaling laws for AV prediction with larger models.\n\n## 📝 Algorithm Problem\n- [LeetCode 1. Two Sum](https://leetcode.com/problems/two-sum/)\n- [LeetCode 2. Add Two Numbers](https://leetcode.com/problems/add-two-numbers/)\n- [LeetCode 3. Longest Substring Without Repeating Characters](https://leetcode.com/problems/longest-substring-without-repeating-characters/)\n- [LeetCode 4. Median of Two Sorted Arrays](https://leetcode.com/problems/median-of-two-sorted-arrays/)\n- [LeetCode 5. Longest Palindromic Substring](https://leetcode.com/problems/longest-palindromic-substring/)\n- [LeetCode 10. Regular Expression Matching](https://leetcode.com/problems/regular-expression-matching/)\n- [LeetCode 15. 3Sum](https://leetcode.com/problems/3sum/)\n- [LeetCode 20. Valid Parentheses](https://leetcode.com/problems/valid-parentheses/)\n- [LeetCode 21. Merge Two Sorted Lists](https://leetcode.com/problems/merge-two-sorted-lists/)\n- [LeetCode 23. Merge k Sorted Lists](https://leetcode.com/problems/merge-k-sorted-lists/)\n- [LeetCode 25. Reverse Nodes in k-Group](https://leetcode.com/problems/reverse-nodes-in-k-group/)\n- [LeetCode 33. Search in Rotated Sorted Array](https://leetcode.com/problems/search-in-rotated-sorted-array/)\n- [LeetCode 41. First Missing Positive](https://leetcode.com/problems/first-missing-positive/)\n- [LeetCode 42. Trapping Rain Water](https://leetcode.com/problems/trapping-rain-water/)\n- [LeetCode 53. Maximum Subarray](https://leetcode.com/problems/maximum-subarray/)\n- [LeetCode 56. Merge Intervals](https://leetcode.com/problems/merge-intervals/)\n- [LeetCode 57. Insert Interval](https://leetcode.com/problems/insert-interval/)\n- [LeetCode 70. Climbing Stairs](https://leetcode.com/problems/climbing-stairs/)\n- [LeetCode 72. Edit Distance](https://leetcode.com/problems/edit-distance/)\n- [LeetCode 76. Minimum Window Substring](https://leetcode.com/problems/minimum-window-substring/)\n- [LeetCode 84. Largest Rectangle in Histogram](https://leetcode.com/problems/largest-rectangle-in-histogram/)\n- [LeetCode 85. Maximal Rectangle](https://leetcode.com/problems/maximal-rectangle/)\n- [LeetCode 94. Binary Tree Inorder Traversal](https://leetcode.com/problems/binary-tree-inorder-traversal/)\n- [LeetCode 101. Symmetric Tree](https://leetcode.com/problems/symmetric-tree/)\n- [LeetCode 102. Binary Tree Level Order Traversal](https://leetcode.com/problems/binary-tree-level-order-traversal/)\n- [LeetCode 104. Maximum Depth of Binary Tree](https://leetcode.com/problems/maximum-depth-of-binary-tree/)\n- [LeetCode 114. Flatten Binary Tree to Linked List](https://leetcode.com/problems/flatten-binary-tree-to-linked-list/)\n- [LeetCode 121. Best Time to Buy and Sell Stock](https://leetcode.com/problems/best-time-to-buy-and-sell-stock/)\n- [LeetCode 124. Binary Tree Maximum Path Sum](https://leetcode.com/problems/binary-tree-maximum-path-sum/)\n- [LeetCode 128. Longest Consecutive Sequence](https://leetcode.com/problems/longest-consecutive-sequence/)\n- [LeetCode 139. Word Break](https://leetcode.com/problems/word-break/)\n- [LeetCode 141. Linked List Cycle](https://leetcode.com/problems/linked-list-cycle/)\n- [LeetCode 146. LRU Cache](https://leetcode.com/problems/lru-cache/)\n- [LeetCode 149. Max Points on a Line](https://leetcode.com/problems/max-points-on-a-line/)\n- [LeetCode 152. Maximum Product Subarray](https://leetcode.com/problems/maximum-product-subarray/)\n- [LeetCode 155. Min Stack](https://leetcode.com/problems/min-stack/)\n- [LeetCode 160. Intersection of Two Linked Lists](https://leetcode.com/problems/intersection-of-two-linked-lists/)\n- [LeetCode 169. Majority Element](https://leetcode.com/problems/majority-element/)\n- [LeetCode 198. House Robber](https://leetcode.com/problems/house-robber/)\n- [LeetCode 200. Number of Islands](https://leetcode.com/problems/number-of-islands/)\n- [LeetCode 206. Reverse Linked List](https://leetcode.com/problems/reverse-linked-list/)\n- [LeetCode 207. Course Schedule](https://leetcode.com/problems/course-schedule/)\n- [LeetCode 208. Implement Trie (Prefix Tree)](https://leetcode.com/problems/implement-trie-prefix-tree/)\n- [LeetCode 215. Kth Largest Element in an Array](https://leetcode.com/problems/kth-largest-element-in-an-array/)\n- [LeetCode 221. Maximal Square](https://leetcode.com/problems/maximal-square/)\n- [LeetCode 224. Basic Calculator](https://leetcode.com/problems/basic-calculator/)\n- [LeetCode 226. Invert Binary Tree](https://leetcode.com/problems/invert-binary-tree/)\n- [LeetCode 236. Lowest Common Ancestor of a Binary Tree](https://leetcode.com/problems/lowest-common-ancestor-of-a-binary-tree/)\n- [LeetCode 239. Sliding Window Maximum](https://leetcode.com/problems/sliding-window-maximum/)\n- [LeetCode 240. Search a 2D Matrix II](https://leetcode.com/problems/search-a-2d-matrix-ii/)\n- [LeetCode 253. Meeting Rooms II](https://leetcode.com/problems/meeting-rooms-ii/)\n- [LeetCode 283. Move Zeroes](https://leetcode.com/problems/move-zeroes/)\n- [LeetCode 295. Find Median from Data Stream](https://leetcode.com/problems/find-median-from-data-stream/)\n- [LeetCode 297. Serialize and Deserialize Binary Tree](https://leetcode.com/problems/serialize-and-deserialize-binary-tree/)\n- [LeetCode 300. Longest Increasing Subsequence](https://leetcode.com/problems/longest-increasing-subsequence/)\n- [LeetCode 301. Remove Invalid Parentheses](https://leetcode.com/problems/remove-invalid-parentheses/)\n- [LeetCode 312. Burst Balloons](https://leetcode.com/problems/burst-balloons/)\n- [LeetCode 315. Count of Smaller Numbers After Self](https://leetcode.com/problems/count-of-smaller-numbers-after-self/)\n- [LeetCode 322. Coin Change](https://leetcode.com/problems/coin-change/)\n- [LeetCode 394. Decode String](https://leetcode.com/problems/decode-string/)\n- [LeetCode 416. Partition Equal Subset Sum](https://leetcode.com/problems/partition-equal-subset-sum/)\n- [LeetCode 438. Find All Anagrams in a String](https://leetcode.com/problems/find-all-anagrams-in-a-string/)\n- [LeetCode 452. Minimum Number of Arrows to Burst Balloons](https://leetcode.com/problems/minimum-number-of-arrows-to-burst-balloons/)\n- [LeetCode 461. Hamming Distance](https://leetcode.com/problems/hamming-distance/)\n- [LeetCode 543. Diameter of Binary Tree](https://leetcode.com/problems/diameter-of-binary-tree/)\n- [LeetCode 560. Subarray Sum Equals K](https://leetcode.com/problems/subarray-sum-equals-k/)\n- [LeetCode 581. Shortest Unsorted Continuous Subarray](https://leetcode.com/problems/shortest-unsorted-continuous-subarray/)\n- [LeetCode 621. Task Scheduler](https://leetcode.com/problems/task-scheduler/)\n- [LeetCode 647. Palindromic Substrings](https://leetcode.com/problems/palindromic-substrings/)\n- [LeetCode 739. Daily Temperatures](https://leetcode.com/problems/daily-temperatures/)\n- [LeetCode 836. Rectangle Overlap](https://leetcode.com/problems/rectangle-overlap/)\n\n## 🎓 Interview Questions\n\n### Perception Engineer\n- Describe common point cloud filtering methods (voxel, statistical, pass-through) and their applicable scenarios\n- Design a point cloud ground segmentation algorithm to solve complex terrain problems\n- How to improve point cloud object detection accuracy? Describe feature extraction and classifier design process\n- Implement KD-Tree based nearest neighbor search to calculate k nearest points for a given point\n- Implement lane line detection algorithm (using OpenCV perspective transform and Hough transform)\n- How to solve camera image quality degradation in rain/fog? Design multi-modal fusion scheme\n- In YOLO model, how to design loss function to improve small object detection accuracy?\n- Explain BEVDet perception algorithm principle, including feature extraction, BEV conversion and detection head design\n- Design camera and LiDAR extrinsic calibration scheme, including calibration board selection and optimization method\n- In multi-sensor fusion system, how to handle time synchronization problem? Compare hardware and software synchronization schemes\n- Implement Kalman filter based sensor data fusion, fusing millimeter-wave radar and camera target position information\n\n### Decision \u0026 Planning Engineer\n- Compare Dijkstra, A*, RRT* algorithms advantages and disadvantages in autonomous driving path planning and applicable scenarios\n- Design highway automatic lane change decision algorithm, considering front/rear vehicle distance, speed difference and safety gap\n- Implement a trajectory planner to generate smooth vehicle trajectory (continuous curvature) satisfying vehicle dynamics constraints\n- Design unprotected left turn decision logic, considering oncoming traffic, pedestrians, traffic signals and road rules\n- In urban roads, how to handle \"ghost probe\" (suddenly appearing pedestrian) situation? Design emergency decision mechanism\n- Implement reinforcement learning based decision system to solve complex intersection traffic problem (reward function design, state representation)\n- Design vehicle intent prediction model, predict other vehicles driving intention based on historical trajectory and surrounding environment\n- How to integrate traffic rules (right of way, speed limit) into decision system? Design rule engine\n- In multi-agent scenarios, how to handle other vehicles not following traffic rules? Design robust decision strategy\n\n### Control Engineer\n- Establish vehicle two-degree-of-freedom dynamics model (bicycle model), derive state equation and control input\n- In vehicle steering control, how to handle \"understeer\" and \"oversteer\" problems? Design compensation strategy\n- Derive relationship between vehicle sideslip angle, yaw rate and steering wheel angle\n- Design LQR-based vehicle lateral controller (lane keeping), including state selection, weight matrix design and discretization implementation\n- Implement model predictive control (MPC) to solve vehicle longitudinal control (car following) problem, considering actuator delay and road slope\n- How to adjust PID controller parameters to adapt to different speeds and road conditions? Design adaptive PID strategy\n- Design automatic parking control system to implement parallel and perpendicular parking functions, considering parking space detection and trajectory planning\n- In high-speed driving, how to handle front wheel blowout and other emergency situations? Design emergency control strategy\n- Implement vehicle stability control (ESC) to prevent sideslip and tail swing, design control algorithm based on tire force observation\n\n### System Development (C++ Direction)\n- Describe differences and usage scenarios of C++ four smart pointers (shared_ptr/unique_ptr/weak_ptr/auto_ptr)\n- Implement thread-safe singleton pattern (C++11+), considering double-checked locking and static local variable schemes\n- Explain RAII (Resource Acquisition Is Initialization) principle and how to apply it in autonomous driving system?\n- How does memory alignment affect point cloud processing performance? Take Eigen library matrix as example\n- Design efficient obstacle trajectory data structure to support real-time query and update\n- Implement a memory pool to manage frequently allocated and released small objects in autonomous driving system\n- Design software architecture of autonomous driving perception system, considering multi-threading, data pipeline and error handling\n- How to design modular system to achieve low coupling and high cohesion between perception, decision and control modules?\n- When deploying deep learning models on embedded platforms (such as Jetson AGX), what optimizations are needed?\n\n### Embedded Software Engineer\n- Explain the difference between RTOS (real-time operating system) and general operating system, why is it important in autonomous driving?\n- Design multi-level interrupt system to ensure real-time performance of critical tasks (such as braking control), using Cortex-M NVIC priority grouping\n- In multi-core RTOS, how to implement inter-task communication and synchronization? Compare mailbox, semaphore and message queue schemes\n- Describe CAN bus frame structure, compare differences and applicable scenarios between standard frame and extended frame\n- Implement CAN bus communication protocol, including ID allocation, arbitration mechanism and error handling\n- Design vehicle system diagnosis scheme based on UDS (Unified Diagnostic Services), implement fault code reading and clearing\n- Write GPIO control program to implement vehicle lights, wipers and other peripheral control\n- Design ADC sampling program to read vehicle sensor (such as tire pressure, oil temperature) data, considering anti-interference and precision optimization\n- In embedded systems, how to handle power management? Design low-power mode and wake-up mechanism\n\n### SLAM \u0026 Localization Engineer\n- Describe ORB-SLAM2/3 system workflow, including feature extraction, tracking, local mapping and loop closure detection\n- How to solve scale drift problem in visual SLAM? Compare monocular, stereo and RGB-D schemes\n- In dynamic scenes, how to detect and remove moving objects? Design method based on optical flow and semantic segmentation\n- Implement key point cloud processing part of LOAM or Lego-LOAM algorithm, including feature extraction and matching\n- In LiDAR SLAM, how to handle point cloud distortion caused by vehicle motion? Design motion compensation scheme\n- Compare advantages and disadvantages of LiDAR-SLAM and visual-SLAM, how to fuse them in autonomous driving?\n- Design visual+IMU+RTK+LiDAR fusion localization system, including time synchronization and extrinsic calibration\n- Implement EKF/UKF-based multi-sensor fusion localization, fusing GPS, IMU and wheel speedometer data\n- In urban canyon and tunnel where GPS signal is lost, how to ensure localization accuracy? Design auxiliary localization scheme\n\n### HD Map Engineer\n- Design high-precision map construction process based on LiDAR point cloud, including point cloud registration, feature extraction and map element generation\n- How to evaluate HD map quality? Design evaluation metrics for accuracy, completeness and consistency\n- In map construction, how to handle dynamic obstacles (such as moving vehicles)? Design dynamic object filtering and completion scheme\n- Design efficient lane-level map data structure to support fast query and update\n- How to implement incremental update of HD map? Design difference detection and transmission scheme to reduce bandwidth consumption\n- On embedded devices, how to optimize map storage and retrieval? Design hierarchical indexing and caching mechanism\n- Describe application scenarios of HD map in autonomous driving, such as localization, path planning and decision-making\n- How to encode traffic rules (no left turn, speed limit) into HD map? Design map semantic representation\n- In autonomous driving system, how to achieve fast matching (localization) between map and vehicle position? Design efficient search algorithm\n\n### Testing Engineer\n- Design test case library for L4 autonomous driving system, covering perception, decision and control functions\n- How to test autonomous driving system performance in extreme weather (heavy rain, dense fog, ice and snow)? Design test scenarios\n- Implement scenario-based testing to test autonomous driving system decision logic\n- Compare V (verification) and V (validation) processes in autonomous driving testing, explain their respective purposes and methods\n- Design safety testing scheme for autonomous driving system to verify safety degradation mechanism in failure situations\n- In HIL (hardware-in-the-loop) testing, how to simulate sensors and actuators? Design test platform\n- Design risk matrix for autonomous driving testing, identify high-risk scenarios and formulate testing strategies\n- In real vehicle testing, how to collect and analyze data to optimize algorithms? Design data collection and analysis process\n- For the \"long-tail problem\" (rare but dangerous scenarios) of autonomous driving system, how to design test cases?\n\n### Model Deployment \u0026 Optimization Engineer\n- Design model quantization scheme (FP32→FP16→INT8) to improve inference speed while maintaining accuracy\n- Implement model pruning to remove redundant parameters and reduce model size, design pruning criteria and fine-tuning strategy\n- In model distillation, how to design teacher model and student model? How to choose distillation loss function?\n- For autonomous driving perception model, design model parallelism and data parallelism scheme to improve multi-GPU inference efficiency\n- Implement ONNX model to TensorRT conversion and optimization, configure appropriate workspace and precision mode\n- On embedded platform, how to optimize model inference performance? Compare GPU, NPU and CPU schemes\n- Design autonomous driving model service architecture to support high concurrency and low latency inference\n- In end-to-end system, how to optimize data preprocessing and post-processing pipeline to reduce overall latency?\n- Implement model hot update, update model without restarting service to ensure service continuity\n\n### General Questions\n- What is the core difference between process and thread? How to choose in actual development?\n- What are the inter-process communication (IPC) methods? Their advantages and disadvantages and applicable scenarios?\n- What is the working principle of virtual memory? Why do we need virtual memory?\n- What is deadlock? What are the four necessary conditions for deadlock? How to avoid deadlock?\n- What is the difference between user mode and kernel mode? How to switch?\n- What is the difference and correspondence between OSI seven-layer model and TCP/IP four-layer model?\n- What is the process of TCP three-way handshake? Why do we need three-way handshake?\n- How does TCP ensure reliable data transmission? What are the mechanisms?\n- What is the difference between HTTP and HTTPS? What is the working principle of HTTPS?\n- Complete process from entering URL to page display?\n- What is the core idea of Von Neumann architecture?\n- What is the composition and working principle of CPU?\n- What is the working principle of Cache? Cache hit rate and failure types?\n- What is the role of memory alignment? How does it affect program performance?\n- What is the principle and role of DMA technology? Why can it improve IO performance?\n- What is the difference and applicable scenarios between TCP and UDP?\n- What are the common page replacement algorithms? Why is LRU commonly used?\n- What are common HTTP status codes and their meanings?\n- What are critical resources and critical sections? How to solve critical section problem?\n- What are the classification and role of bus? Differences between data bus, address bus and control bus?\n\n### C++\n- [C++ High-frequency Interview Questions](https://github.com/0voice/cpp-learning-2025/blob/main/interview_questions/README.en.md)\n\n\n\n## 💼 Job Board\n\n\n\n- **Waymo** – [Apply Here](https://waymo.com/careers/)\n- **Cruise** – [Apply Here](https://getcruise.com/careers/)\n- **Zoox** – [Apply Here](https://zoox.com/careers)\n- **Aurora** – [Apply Here](https://aurora.tech/careers/)\n- **NVIDIA** – [Apply Here](https://nvidia.com/en-us/about-nvidia/careers/) \n- **Motional** – [Apply Here](https://motional.com/careers)\n- **Applied Intuition** – [Apply Here](https://www.appliedintuition.com/careers)\n- **Waabi** – [Apply Here](https://waabi.ai/careers/)\n- **Oxa** – [Apply Here](https://oxa.tech/careers/)\n\n\n## 🤝 Community \u0026 Contribution\n\n\n\nThank you for visiting!  \nThis repo aims to be the strongest C++ autonomous driving resource collection worldwide.\n\nContributions of any kind are extremely welcome — new projects, fixes, translations, interview questions, etc.\n\nStar \u0026 Watch so you never miss an update!\n\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/0voice%2Fawesome-autonomous-driving-cpp/projects"}