Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

Awesome-Autonomous-Driving

https://github.com/PeterJaq/Awesome-Autonomous-Driving

Last synced: 5 days ago
JSON representation

Update
- 2023/12/3
1. Autonomous Driving Midleware and Integrated Solutions
- 1.1 Midelware
  - Cyber - High performance runtime framework designed specifically for autonomous driving (AD) scenarios from [baidu](www.baidu.com).
  - ROS - A set of software libraries and tools that help you build robot applications.
  - ROS-2 - A set of software libraries and tools that help you build robot applications.
- 1.2 Integrated Solutions
  - Apollo - The intergrated solution from [baidu](www.baidu.com).
  - AutowareArchitectureProposal.proj - Manages several projects related to self-driving vehicles.
  - self-driving-ish_computer_vision_system - This project generates images you've probably seen in autonomous driving demo.
  - Aslan - An open-source full-stack software based on ROS framework.
  - AutoC2X-AW - Extension for Autoware and OpenC2X.
  - Autoware.auto - Open-source software for self-driving vehicles known as Autoware-2.
  - Autoware.ai - Open-source software for self-driving vehicles known as Autoware-1.
2. Sensor and Calibration Tools
- 2.1 Sensor Hardware
  - velodyne - velodyne lidar driver for ros.
  - livox_ros_driver - livox (a low cost lidar form [DJI](https://www.dji.com/cn)) lidar driver.
  - rslidar_sdk - lidar driver from [Robosense](https://www.robosense.ai).
  - ros2_ouster_drivers - ROS2 Drivers for the [Ouster](https://www.ouster.com) OS-0, OS-1, and OS-2 Lidars.
  - miivii_gmsl_camera - [米文](https://www.miivii.com/)摄像头
  - usb_cam - all most ros1 usb camera driver you can buy from Taobao/Aliexpress.
  - ros2_usb_camera - all most ros2 usb camera driver you can buy from Taobao/Aliexpress.
  - novatel_gps_driver - C++ ROS driver for NovAtel GPS / GNSS Receivers.
  - STM32Cube_MCU_Overall_Offer - The open source offer for the STM32 MCU products.
  - sensing - [森云](https://www.sensing-world.com/) - 森云摄像头
  - Hikvision - You can download [SDK](https://www.hikvision.com/en/support/download/sdk/).
  - huace - 华测组合导航产品
  - huace - 华测组合导航产品
- 2.2 Calibration Tools
3. Perception
- 3.1.1 Vision based
  - Next-ViT
  - FocalsConv
  - PoolFormer
  - OccDepth - Aware Method for 3D Semantic Scene Completion.
  - VoxFormer - based 3D Semantic Scene.
  - TPVFormer - Perspective View for Vision-Based 3D Semantic Occupancy Prediction.
  - SurroundOcc - Camera 3D Occupancy Prediction for Autonomous Driving.
  - rising
  - Advanced-Lane-Detection - 一个非常适合新人的车道检测任务的小demo
  - RESA
  - LaneDet
  - CondLaneNet
  - LaneNet-Lane-Detection
  - urban_road_filter
  - Cam2BEV - Cam2BEV一个将多路周视摄像头的语义分割结果融合在一个鸟瞰图的工具，并且该方法不需要手工对鸟瞰图进行标注通过合成的数据进行训练。
  - YOLOP - 来自华中科技大学的作品，也是yolo系列的另一力作，本项目提出额一种高效的多任务网络，可以联合处理自动驾驶中的多个任务（目标检测，可行驶区域分割与车道检测三个关键任务），值得注意的是在BDD100K中该方法实现了SOTA的情况下还保持了嵌入式友好。
  - YOLOR - 提出了在网络模型中引入隐知识的概念，将隐知识和显知识同时作用于模型训练，通过核函数对齐，预测精修以及多任务同时学习，让网络表征出一种统一化的特征。
  - YOLOX - Anchor-free 版本的YOLO，堆砌了解耦头，simOTA等，达到了SOTA
  - 3D-BoundingBox
  - Pseudo_Lidar_V2 - Accurate Depth for 3D Object Detection in Autonomous Driving.
  - BoxeR - Attention for 2D and 3D Transformers. 从鸟瞰平面生成判别信息，用于 3D 端到端对象检测。该项目同样也提出了2D上的Detection 解决方案。
  - Next-ViT
  - CoAtNet
  - ConvNext
  - Up to 31
  - Occupancy Networks
  - Pyramid Occupancy Network
  - A Comprehensive Review of Occupancy
  - Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
  - https://arxiv.org/abs/2203.10981 - Aware Transformer 基于单目的Depth-Aware Transformer 的3D检测.
  - AlignMixup
  - MonoScene
  - Pseudo_lidar - Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving.
  - Mobile-Former - Former，MobileNet和Transformer的并行设计，可以实现局部和全局特征的双向融合，在分类和下游任务中，性能远超MobileNetV3等轻量级网络！
  - CoAtNet
- 3.1.2 Lidar based
  - Voxelnet
  - Complex-YOLO
  - PointRCNN
  - CenterPoint - 3D Object Detection and Tracking using center points in the bird-eye view.
  - PartA2-Net - From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network.
  - CIA-SSD - Confident IoU-Aware Single Stage Object Detector From Point Cloud.
  - SFA3D - Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds.
  - Auto4D - Auto4D: Learning to Label 4D Objects from Sequential Point Clouds.
  - patchwork - GPF）和地面似然估计（GLE) IROS2021
  - patchwork++ - VPF）、自适应GLE（A-GLE）和空间地面恢复（TGR）的新模块组成。Patchwork++具有更高的精确度和召回率。此外，新的Patchwork++具有较低的召回标准差。
  - Auto4D - Auto4D: Learning to Label 4D Objects from Sequential Point Clouds.
  - 3DAL - Offboard 3D Object Detection from Point Cloud Sequences
  - LIFT
  - VoxelNext
  - PillarNext
  - LargeKernel3D
  - LinK - Based 3D Perception
  - Spherical Transformer - Based 3D Recognition
  - Unspervised 3D OD
  - Benchmarking robustness of 3D OD
  - Bi3D - Domain Active Learning for Cross-Domain 3D Object Detection
  - Density-Insensitive - Insensitive Unsupervised Domain Adaption on 3D Object Detection
  - UniDistill - Modality Knowledge Distillation Framework for 3D Object Detection in Bird’s-Eye View
  - MSF - Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences
  - OcTr - Based Transformer for 3D Object Detection
  - SlowLiDAR - Based Detection Using Adversarial Examples
  - Uni3D - Dataset 3D Object Detection
  - DetZero - term Sequential Point Clouds
  - FocalFormer3D
  - GPA-3D - aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
  - KECOR
  - Once Detected, Never Lost
  - PARTNER
  - PG-RCNN - RCNN: Semantic Surface Point Generation for 3D Object Detection
  - Domain-Adaptive - Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
  - RangeView
  - 3DIoUMatch-PVRCNN - 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection.
  - TRAVEL
  - 3DIoUMatch-PVRCNN - 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection.
  - FSD - stride Sparse Transformer 来自图森的 Sparse Transformer.
- 3.1.2 Multi Sensor Fusion
  - ST-P3 - to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
  - SpatialDETR - Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention
  - BEVDet - Performance Multi-Camera 3D Object Detection in Bird-Eye-View.
  - BEVerse - Eye-View for Vision-Centric Autonomous Driving.
  - PolarFormer - camera 3D Object Detection with Polar Transformers.
  - CrossDTR - view and Depth-guided Transformers for 3D Object Detection.
  - Sim-BEV
  - AeDet - invariant Multi-view 3D Object Detection.
  - PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformer
  - BEVDet4D - camera 3D Object Detection.
  - M2BEV - Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation.
  - PolarDETR - based Surround-View 3D Detection.
  - Understand BEV - Eye-View Representations in Autonomous Driving
  - BEVHeight - Based Roadside 3D Object Detection
  - BEV-SAN - SAN: Accurate BEV 3D Object Detection via Slice Attention Networks
  - Collaboration Overtake LiDAR
  - MSMDFusion - Depth Seeds for 3D Object Detection
  - BEV-Guided - Guided Multi-Modality Fusion for Driving Perception
  - BEV-DC - Eye View Assisted Training for Depth Completion
  - Ada3D
  - Cross Modal Transformer
  - Object-Centric Temporal Modeling - Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
  - QD-BEV - aware View-guided Distillation for Multi-view 3D Object Detection
  - MetaBEV
  - Perceiver
  - MonoNeRD - like Representations for Monocular 3D Object Detection
  - Object as Query
  - Predict to Detect - guided 3D Object Detection using Sequential Images
  - Pepresentation Disparity-aware - aware Distillation for 3D Object Detection
  - SA-BEV - BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection
  - SparseBEV - Performance Sparse 3D Object Detection from Multi-Camera Videos
  - SparseFusion - Modal Sparse Representations for Multi-Sensor 3D Object Detection
  - SupFusion - Camera Fusion for 3D Object Detection
  - 3DPPE - Camera 3D Object Detection Transformers
  - MonoDETR - guided Transformer for Monocular 3D Object Detection
  - PETRv2 - Camera Images
  - UpCycling - supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes
  - Repainting and Imitating Learning for Lane Detection
  - WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labels
  - CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention
  - M^2-3DLaneNet: Multi-Modal 3D Lane Detection
  - RCLane: Relay Chain Prediction for Lane Detection
  - PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
  - Reconstruct from Top View: A 3D Lane Detection Approach based on Geometry Structure Prior
  - Multi-level Domain Adaptation for Lane Detection
  - Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification - Fast-Lane-Detection-v2) TPAMI 2022
  - ONCE-3DLanes: Building Monocular 3D Lane Detection
  - A Keypoint-based Global Association Network for Lane Detection
  - Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
  - SDLane Dataset
  - Towards Driving-Oriented Metric for Lane Detection Models
  - CLRNet: Cross Layer Refinement Network for Lane Detection
  - Rethinking Efficient Lane Detection via Curve Modeling
  - Lane detection with Position Embedding
  - Laneformer: Object-Aware Row-Column Transformers for Lane Detection
  - RONELDv2: A faster, improved lane tracking method
  - BEV-LaneDet - Points.
  - Anchor3DLane
  - FrustumFormer - Aware Resampling for Multi-View 3D Detection
  - LaserMix - Supervised LiDAR Semantic Segmentation
  - PC Forecasting as Proxy
  - Less is More
  - ISBNet - Aware Sampling and Box-Aware Dynamic Convolution
  - Focal Knowledge Form
  - BEVFusion - agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes.
  - BEVDepth
  - BEVFormer
  - BEVFormer
  - AtrousFormer：Lane Detection with Versatile AtrousFormer and Local Semantic Guidance
  - PERFv2
- 3.2 Tracking
  - CAMO-MOT - [3D-MOT] This paper propose an occlusion head to select the best object appearance features multiple times effectively, reducing the influence of occlusions
  - EagerMot - [3D-MOT] Improve your online 3D multi-object tracking performance by using 2D detections to support tracking when 3D association fails.
  - OGR3MOT - [3D-MOT] This paper provides a natural way for track initialization and handling of false positive detections.
  - Tracking ROS
  - CAMO-MOT - [3D-MOT] This paper propose an occlusion head to select the best object appearance features multiple times effectively, reducing the influence of occlusions
  - OGR3MOT - [3D-MOT] This paper provides a natural way for track initialization and handling of false positive detections.
  - 3D Multi-Object Tracking in Point Clouds Based on Prediction Confidence-Guided Data Association
  - Label Metric for Multi-Class Multi-Target Tracking under Hierarchical Multilevel Classification
  - CXTrack
  - Monocular-Tracking - Aware Matching for Monocular 3D Object Tracking
  - MBPTrack
  - Synchronize Feature Extracting and Matching
  - ImmortalTracker - Our mismatch ratio is tens of times lower than any previously published method.
  - Yolov5_DeepSort_Pytorch - 基于yolo-v5的目标追踪
  - SimpleTrack - [3D-MOT] Simple yet Effective 3D Multi-object Tracking.
  - Label Metric for Multi-Class Multi-Target Tracking under Hierarchical Multilevel Classification
- 3.4 High Performance Inference
  - TRT ViT
  - CUDA-PointPillars - NV官方PointPillars部署方案
  - nutonomy_pointpillars - PointPillars
  - mmdet3d_onnx_tools - PointPillars
  - CenterPoint - CenterPoint-PonintPillars
  - PointPillars_MultiHead_40FPS - MultiHead PointPillars
  - 我自己的 ROS Lidar Perception TensorRT部署
  - multi-attention -> onnx
  - Lite.ai
  - CenterPoint - CenterPoint 推理方案 ROS
  - TRT ViT
- 3.3 Map & Topo
  - MapNeXt
  - PolyRoad - Boundary Detection
  - Survey - Definition Maps Construction Based on Visual Sensor: A Comprehensive Survey
  - VMA - and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
  - Lane Graph as Path - preserving Path-wise Modeling for Online Lane Graph Construction
  - PivotNet - to-end HD Map Construction
  - E2E Map - to-End Vectorized HD-map Construction with Piecewise Bezier Curve
  - LATR
  - TopoReas - based Topology Reasoning for Driving Scenes
  - TopoMLP
  - Neural Map Prior
  - Construction using Geometry
  - MapTRv2 - to-End Framework for Online Vectorized HD Map Construction
  - InstaGraM - level Graph Modeling for Vectorized HD Map Learning
  - PolyMerge
  - MapSeg
  - Efficient - Eye-View
  - Mind the map!
  - ScalableMap - Range Vectorized HD Map Construction
  - TopoNet
  - SuperFusion - Camera Fusion for Long-Range HD Map Generation
  - MapTR
  - VectorMapNet - to-end Vectorized HD Map Learning
  - csBoundary - Scale Road-Boundary Detection in Aerial Images for High-Definition Maps
  - Survey - Definition Maps Furniture – A Survey
  - Topo-boundary - boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving
  - HDMapNet
4. Prediction
- 3.4 High Performance Inference
  - VectorNet
  - TNT - TNT是一种基于历史数据（即多代理和环境之间交互）生成目标的轨迹状态序列方法，并基于似然估计得到紧凑的轨迹预测集。
  - DESIRE - DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
  - TNT: Target-driveN Trajectory Prediction - TNT的轨迹生成利用了TNT的方法.
  - MultiPath++ - Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction.
  - MotionCNN - A Strong Baseline for Motion Prediction in Autonomous Driving.
  - WAT - Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction.
  - BEVerse - Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving.
  - ParkPredict+ - Vehicle simualtion and behavior prediction in parking lots.
  - HiVT - Hierarchical Vector Transformer for Multi-Agent Motion Prediction
  - VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation - 与目标物信息进对目标进行行为预测。apollo在7.0版本的行为预测部分的encoder利用了这个vectornet.
  - FEND - Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction
  - EqMotion - Agent Motion Prediction With Invariant Interaction Reasoning
  - EigenTrajectory - Rank Descriptors for Multi-Modal Trajectory Forecasting
  - Temporal Enhanced - view 3D Object Detector via Historical Object Prediction
  - TrajectoryFormer
  - VectorNet
  - TNT - TNT是一种基于历史数据（即多代理和环境之间交互）生成目标的轨迹状态序列方法，并基于似然估计得到紧凑的轨迹预测集。
  - TNT: Target-driveN Trajectory Prediction - TNT的轨迹生成利用了TNT的方法.
5 Localization and SLAM
- 3.4 High Performance Inference
  - hdl_localization - **Lidar + IMU** 基于卡尔曼滤波的位置估计使用了激光雷达，IMU, 可以做到实时估计。
  - PaGO-LOAM - LOAM的LiDAR测距框架，在这个框架中，测试地面分割算法是否有助于提取特征和改善SLAM性能是很容易和直接的。
  - Quatro-LeGO-LOAM - LOAM
  - AVP-SLAM-SIM - SLAM-PLUS](https://github.com/liuguitao/AVP-SLAM-PLUS)
  - DeepLIO - **Lidar + IMU** 一款基于深度学习的lidar IMU融合里程计
  - hdl_graph_slam - **Lidar + IMU + GPS** 它基于三维图形SLAM，具有基于NDT扫描匹配的测距估计和循环检测。它还支持几个约束，如GPS、IMU。
  - LIO-SAM - **Lidar + IMU + GPS** 基于激光雷达，IMU和GPS多种传感器的因子图优化方案，以及在帧图匹配中使用帧-局部地图取代帧-全局地图。
  - LVI-SAM - **Lidar + Camera** 基于视觉+激光雷达的惯导融合
  - LeGO-LOAM - **Lidar** LeGO-LOAM是以LOAM为框架而衍生出来的新的框架。其与LOAM相比，更改了特征点的提取形式，添加了后端优化，因此，构建出来的地图就更加的完善。
  - SC-LeGO-LOAM - **Lidar** LeGO-LOAM的基于全局描述子Scan Context的回环检测
  - SC-LIO-SAM - **Lidar + Camera** LIO-SAM的基于全局描述子Scan Context的回环检测
  - Livox-Mapping - **Livox + IMU + SC ** 一款基于Livox的mapping工具包，在先前的工具上添加了SC和Fastlio的一些特性
  - Fast-LIO - 目前最好用的前端里程计之一，几乎同时兼具速度与鲁棒性
  - Faster-LIO - 比Fast LIO快1-1.5倍的前端里程计
  - FAST_LIO_SLAM
  - SC-A-LOAM - Scancontext + 现在的SOTA里程计(Lego-loam, fast lio, a loam etc.)
  - FAST_LIO_LOCALIZATION
  - Deep Functional Maps
  - AVP-SLAM - SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot(IROS 2020),主要是通过BEV视角对停车场中的车道线车库线以及标识进行检测并利用其进行稀疏定位。
  - vMap
  - DeepLSD
  - EgoLoc
6. Planning
- 3.4 High Performance Inference
  - pacmod - Designed to allow the user to control a vehicle with the PACMod drive-by-wire system.
  - rrt - C++ RRT (Rapidly-exploring Random Tree) implementation.
  - path_planner - Hybrid A* Path Planner for the KTH Research Concept Vehicle.
  - fastrack - A ROS implementation of Fast and Safe Tracking (FaSTrack).
  - traffic-editor - A graphical editor for robot traffic flows.
  - steering_functions - Contains a C++ library that implements steering functions for car-like robots with limited turning radius.
  - flexible-collision-library - A library for performing three types of proximity queries on a pair of geometric models composed of triangles.
  - aikido - Artificial Intelligence for Kinematics, Dynamics, and Optimization.
  - casADi - A symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs.
  - ACADO Toolkit - A software environment and algorithm collection for automatic control and dynamic optimization.
  - CrowdNav - Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning.
  - ompl - Consists of many state-of-the-art sampling-based motion planning algorithms.
  - openrave - Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.
  - teb_local_planner - An optimal trajectory planner considering distinctive topologies for mobile robots based on Timed-Elastic-Bands.
  - pinocchio - A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives.
  - rmf_core - The rmf_core packages provide the centralized functions of the Robotics Middleware Framework (RMF).
  - global_racetrajectory_optimization - This repository contains multiple approaches for generating global racetrajectories.
  - toppra - A library for computing the time-optimal path parametrization for robots subject to kinematic and dynamic constraints.
  - tinyspline - TinySpline is a small, yet powerful library for interpolating, transforming, and querying arbitrary NURBS, B-Splines, and Bézier curves.
  - dual quaternions ros - ROS python package for dual quaternion SLERP.
  - ilqr - Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models.
  - EGO-Planner - A lightweight gradient-based local planner without ESDF construction, which significantly reduces computation time compared to some state-of-the-art methods.
  - pykep - A scientific library providing basic tools for research in interplanetary trajectory design.
  - am_traj - Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight.
  - GraphBasedLocalTrajectoryPlanner - Was used on a real race vehicle during the Roborace Season Alpha and achieved speeds above 200km/h.
  - HypridAStarTrailer - A path planning algorithm based on Hybrid A* for trailer truck.
  - moveit - Easy-to-use robotics manipulation platform for developing applications, evaluating designs, and building integrated products.
  - pacmod - Designed to allow the user to control a vehicle with the PACMod drive-by-wire system.
  - mb planner - Aerial vehicle planner for tight spaces. Used in DARPA SubT Challenge.
  - 自动驾驶中的决策规划算法概述
  - mb planner - Aerial vehicle planner for tight spaces. Used in DARPA SubT Challenge.
  - 有限状态机
  - MPC
  - PathPlanning
  - commonroad - Composable benchmarks for motion planning on roads.
  - traffic-editor - A graphical editor for robot traffic flows.
- 3.3 High Performance Inference
  - pacmod - Designed to allow the user to control a vehicle with the PACMod drive-by-wire system.
  - Ruckig - Instantaneous Motion Generation. Real-time. Jerk-constrained. Time-optimal.
7. Control
- 3.4 High Performance Inference
  - Open Source Car Control - An assemblage of software and hardware designs that enable computer control of modern cars in order to facilitate the development of autonomous vehicle technology.
  - control-toolbox - An efficient C++ library for control, estimation, optimization and motion planning in robotics.
  - mpcc - Model Predictive Contouring Controller for Autonomous Racing.
  - open_street_map - ROS packages for working with Open Street Map geographic information.
  - autogenu-jupyter - This project provides the continuation/GMRES method (C/GMRES method) based solvers for nonlinear model predictive control (NMPC) and an automatic code generator for NMPC.
  - OpEn - A solver for Fast & Accurate Embedded Optimization for next-generation Robotics and Autonomous Systems.
  - PID
  - autogenu-jupyter - This project provides the continuation/GMRES method (C/GMRES method) based solvers for nonlinear model predictive control (NMPC) and an automatic code generator for NMPC.
9. Dataset and Competition
- 3.4 High Performance Inference
  - BDD100k
  - SODA10M
  - OPV2V - 首个大型自动驾驶协同感知数据集 + banchmark代码框架, 由UCLA提供
- 3.3 High Performance Inference
  - ONCE
10. Data Loop & Model Loop
- 3.4 High Performance Inference
  - ISNAS-DIP - Specific Neural Architecture Search for Deep Image Prior
  - AirDet - Shot Detection without Fine-tuning for Autonomous Exploration. 这篇文章把他放在数据挖掘方面是思考有没有可能用极少样本不用fine-tuning 后可以从原有自动驾驶数据湖中挖掘出更多的样本。
  - Rethink OOD
  - Data Requirement - Learning Approach to Predicting Performance and Data Requirements
  - Independent Componenet Alignment MT - Task Learning
  - Data-Efficient - Efficient Large Scale Place Recognition With Graded Similarity Supervision
  - AL-FM
  - LfOSA
  - RAC - Tail Visual Recognition*
11. Visualization
- 3.4 High Performance Inference
  - MixSim
  - Uber AVS - 自动驾驶可视化前端组件 xviz 与 streetscape.gl
  - Cruise - Cruise 开源的一款自动驾驶前端可视化套件
  - UniSim - Loop Sensor Simulator
  - LiDar-in-the-loop - in-the-Loop Hyperparameter Optimization
  - Compact Representation
  - The Differentiable Lens

Programming Languages

C++ 63 Python 61 Jupyter Notebook 3 Rust 1 C 1 CMake 1 Shell 1

Ecosyste.ms: Awesome

Awesome-Autonomous-Driving

Update

1. Autonomous Driving Midleware and Integrated Solutions

1.1 Midelware

1.2 Integrated Solutions

2. Sensor and Calibration Tools

2.1 Sensor Hardware

2.2 Calibration Tools

3. Perception

3.1.1 Vision based

3.1.2 Lidar based

3.1.2 Multi Sensor Fusion

3.2 Tracking

3.4 High Performance Inference

3.3 Map & Topo

4. Prediction

3.4 High Performance Inference

5 Localization and SLAM

3.4 High Performance Inference

6. Planning

3.4 High Performance Inference

3.3 High Performance Inference

7. Control

3.4 High Performance Inference

9. Dataset and Competition

3.4 High Performance Inference

3.3 High Performance Inference

10. Data Loop & Model Loop

3.4 High Performance Inference

11. Visualization

3.4 High Performance Inference