自动驾驶的技术栈有哪些？一览近15个方向路线（感知/定位/融合/规控等）

2024年是自动驾驶功能集中爆发的一年，各类主流方案如BEV检测、在线地图、occupancy networks、时序模型都陆续上车，功能层面上越来越接近L3,，甚至L4级别的功能也陆续具备了。可以说，自动驾驶撑起了整个AI领域的半边天，技术之密集，实属罕见！

今天也为大家推荐两个自动驾驶方向的公众号【自动驾驶之心】和【自动驾驶Daily】，专注于自动驾驶技术输出和行业咨询推送，基本完成自动驾驶所有方向的覆盖。

点击关注“自动驾驶之心”，一览最全技术栈

为了方便大家入门学习，自动驾驶之心为大家推出了近13个感知定位融合与标定学习路线，里面的论文和学习资料特别适合刚入门和转行的同学，内容较多，建议大家收藏后反复观看。

（一）3D目标检测系列

1. 3D Object Detection for Autonomous Driving：A Review and New Outlooks
2. 3D Object Detection from Images for Autonomous Driving A Survey
3. A Survey of Robust LiDAR-based 3D Object Detection Methods for autonomous driving
4. A Survey on 3D Object Detection Methods for Autonomous Driving Applications
5. Deep Learning for 3D Point Cloud Understanding：A Survey
6. Multi-Modal 3D Object Detection in Autonomous Driving：a survey
7. Survey and Systematization of 3D Object Detection Models and Methods

（二）BEV感知综述

1. Delving into the Devils of Bird’s-eye-view Perception-A Review, Evaluation and Recipe
2. Surround-View Vision-based 3D Detection for Autonomous Driving：A Survey
3. Vision-Centric BEV Perception：A Survey
4. Vision-RADAR fusion for Robotics BEV Detections：A Survey

（三）传感器标定综述

涉及多相机标定、毫米波与激光雷达标定、相机-激光雷达-毫米波雷达标定、相机-IMU标定、相机标定、鱼眼相机标定、在线标定等；

（四）Occupancy占用网络综述

1. Grid-Centric Traffic Scenario Perception for Autonomous Driving：A Comprehensive Review

（五）多模态融合感知综述

1. Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving：Datasets, Methods, and Challenges
2. MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving：A Review
3. Multi-Modal 3D Object Detection in Autonomous Driving：A Survey
4. Multi-modal Sensor Fusion for Auto Driving Perception：A Survey
5. Multi-Sensor 3D Object Box Refinement for Autonomous Driving
6. Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving

（六）端到端自动驾驶综述

1. End-to-end Autonomous Driving-Challenges and Frontiers
2. Recent Advancements in End-to-End Autonomous Driving using Deep Learning

（七）自动驾驶规划控制综述

1. A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles
2. A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles
3. Mobile Robot Path Planning in Dynamic Environments：A Survey
4. Motion Planning and Control for Mobile Robot Navigation Using Machine Learning：A Survey
5. Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles

（八）CUDA与C++加速

1. Cuda by Example
2. CUDA for Engineers. An Introduction to High-Performance Parallel Computing-Addison Wesley
3. GPU parallel program development using CUDA-CRC Press

（九）大模型与自动驾驶

1. Planning-oriented Autonomous Driving
2. MINIGPT-4: ENHANCING VISION-LANGUAGE UNDERSTANDING WITH ADVANCED LARGE LANGUAGE MODELS
3. LANGUAGEMPC: LARGE LANGUAGE MODELS AS DECISION MAKERS FOR AUTONOMOUS DRIVING
4. HiLM-D: Towards High-Resolution Understanding in Multimodal Large Language Models for Autonomous Driving
5. Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving
6. DRIVEGPT4: INTERPRETABLE END-TO-END AUTONOMOUS DRIVING VIA LARGE LANGUAGE MODEL
7. Drive Like a Human: Rethinking Autonomous Driving with Large Language Models
8. Learning Transferable Visual Models From Natural Language Supervision
9. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
10. BEVGPT: Generative Pre-trained Large Model for Autonomous Driving Prediction, Decision-Making, and Planning

（十）轨迹预测与自动驾驶

1. Survey：Machine Learning for Autonomous Vehicle's Trajectory Prediction
2. Situation Assessment of an Autonomous Emergency
3. Vehicle Trajectory Prediction by Integrating Physics and Maneuver-Based Approaches Using Interactive Multiple Models
4. A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models
5. Vehicle Trajectory Prediction Considering Driver Uncertainty and Vehicle Dynamics Based on Dynamic Bayesian Network
6. Naturalistic Driver Intention and Path Prediction Using Recurrent Neural Networks
7. Intention-Aware Vehicle Trajectory Prediction Based on Spatial-Temporal Dynamic Attention Network for Internet of Vehicles
8. Trajectory Prediction for Autonomous Driving Using Spatial-Temporal Graph Attention Transformer
9. Multi-Vehicle_Collaborative_Learning_for_Trajectory_Prediction_With_Spatio-Temporal_Tensor_Fusion
10. STAG A novel interaction-aware path prediction method based on Spatio-Temporal Attention Graphs for connected automated vehicles
11. TNT Target-driveN Trajectory Prediction
12. DenseTNT End-to-end Trajectory Prediction from Dense Goal Sets

（十一）在线高精地图

（十二）世界模型与自动驾驶

1. ADriver-I: A General World Model for Autonomous Driving
2. DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
3. Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
4. FIERY: Future Instance Prediction in Bird’s-Eye View from Surround Monocular Cameras
5. GAIA-1: A Generative World Model for Autonomous Driving
6. Model-Based Imitation Learning for Urban Driving
7. OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
8. MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations
9. SEM2: Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
10. DREAM TO CONTROL: LEARNING BEHAVIORS BY LATENT IMAGINATION
11. MASTERING ATARI WITH DISCRETE WORLD MODELS
12. LEARNING UNSUPERVISED WORLD MODELS FOR AUTONOMOUS DRIVING VIA DISCRETE DIFFUSION

(十三) NeRF与自动驾驶

1. 3D Gaussian Splatting for Real-Time Radiance Field Rendering
2. Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM
3. F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
4. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
5. MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
6. Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
7. MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
8. Neuralangelo: High-Fidelity Neural Surface Reconstruction
9. UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
10. UniSim: A Neural Closed-Loop Sensor Simulator

公众号后台回复“数据集”获取100+深度学习各方向资源整理