作者丨wanghy@知乎
来源丨https://zhuanlan.zhihu.com/p/432887760
编辑丨3D视觉工坊
特对IROS2021 自动驾驶相关文章进行总结，包括：决策、规划、导航、定位、感知、跟踪、预测、控制等各个方向，本文对论文进行了分类，希望对自动驾驶行业的同行们提供一些有益的参考。完整版的分类论文原文见下方百度网盘链接，github链接：链接：https://pan.baidu.com/share/init?surl=v1RX-wiVxasDzpUCkU5HnQ
提取码：7s1q
代码地址：https://github.com/wanghuayou1028/IROS2021-SLAM-paper-list
Localization:
参考链接：https://zhuanlan.zhihu.com/p/432829868
Perception:3D Radar Velocity Maps for Uncertain Dynamic Environments
A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
A Simple and Efficient Multi-Task Network for 3D Object Detection and Road Understanding
BEV-Net A Bird's Eye View Object Detection Network for LiDAR Point Cloud
CP-Loss Connectivity-Preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images
Fine-Grained Off-Road Semantic Segmentation and Mapping Via Contrastive Learning
LiDAR-Based Drivable Region Detection for Autonomous Driving
Monitoring Object Detection Abnormalities Via Data-Label and Post-Algorithm Abstractions
Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography
RV-FuseNet Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting
SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving
COINet: Adaptive Segmentation with Co-Interactive Network for Autonomous Driving
SNE-RoadSeg+ Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection
Unsupervised Vehicle Re-Identification Via Self-Supervised Metric Learning Using Feature Dictionary
Prediction:Automated Type-Aware Traffic Speed Prediction Based on Sparse Intelligent Camera System
Decoder Fusion RNN Context and Interaction Aware Decoders for Trajectory Prediction
Joint Intention and Trajectory Prediction Based on Transformer
Maneuver-based Trajectory Prediction for Self-driving Cars Using Spatio-temporal Convolutional Networks
Multiple Contextual Cues Integrated Trajectory Prediction for Autonomous Driving
Tracking:Cross-Modal 3D Object Detection and Tracking for Auto-Driving
Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
Score Refinement for Confidence-Based 3D Multi-Object Tracking
Planning:DeepSIL A Software-In-The-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks
Diverse Critical Interaction Generation for Planning and Planner Evaluation
PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
STFP: Simultaneous Traffic Scene Forecasting and Planning for Autonomous Driving
A Novel Recursive Smooth Trajectory Generation Method for Unmanned Vehicles
Intention recognition:A Multimodal and Hybrid Framework for Human Navigational Intent Inference
An Efficient Understandability Objective for Dynamic Optimal Control
CovarianceNet Conditional Generative Model for Correct Covariance Prediction in Human Motion Prediction
GRIT Fast, Interpretable, and Verifiable Goal Recognition with Learned Decision Trees for Autonomous Driving
Interpretable Goal Recognition in the Presence of Occluded Factors for Autonomous Vehicles
Multi-modal Scene-compliant User Intention Estimation in Navigation
Safety-Oriented Pedestrian Occupancy Forecasting
Simultaneous Prediction of Pedestrian Trajectory and Actions Based on Context Information Iterative Reasoning
Control:Semi-Cooperative Control for Autonomous Emergency Vehicles
Navigation:A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
A Kinematic Model for Trajectory Prediction in General Highway Scenarios
A Multi-Objective Path Planning and Exploration Framework for Unknown and Unstructured Environments
Autonomous Drone Racing with Deep Reinforcement Learning
Autonomous Mobile Robot Navigation Independent of Road Boundary Using Driving Recommendation Map
Autonomous Vehicle Navigation in Semi-Structured Environments Based on Sparse Waypoints and LiDAR Road-Tracking
Connecting Deep-Reinforcement-Learning-Based Obstacle Avoidance with Conventional Global Planners Using Waypoint Generators
Context and Orientation Aware Path Tracking
Cooperative Autonomous Vehicles That Sympathize with Human Drivers
Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows
DiGNet Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks
Fast Autonomous Robotic Exploration Using the Underlying Graph Structure
Gaussian Process-based Interpretable Runtime Adaptation for Safe Autonomous Systems Operations in Unstructured Environments
Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph
KB-Tree Learnable and Continuous Monte-Carlo Tree Search for Autonomous Driving Planning
Latent Attention Augmentation for Robust Autonomous Driving Policies
Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain
Learning-Based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
LiDAR Degradation Quantification for Autonomous Driving in Rain
Map-Aided Train Navigation with IMU Measurements
Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
NavTuner Learning a Scene-Sensitive Family of Navigation Policies
On Fault Classification in Connected Autonomous Vehicles Using Output-Only Measurements
Online High-Level Model Estimation for Efficient Hierarchical Robot Navigation
Pallet Detection and Docking Strategy for Autonomous Pallet Truck AGV Operation
Reinforcement Learning Based Negotiation-Aware Motion Planning of Autonomous Vehicles
Road Graphical Neural Networks for Autonomous Roundabout Driving
Robust Policy Search for an Agile Ground Vehicle under Perception Uncertainty
Shape Estimation of Negative Obstacles for Autonomous Navigation
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic An Autonomous Logistic Vehicle for Contactless Goods Transportation
Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
Vulnerability of Connected Autonomous Vehicles Networks to Periodic Time-Varying Communication Delays of Certain Frequency
Modeling:A High-Accuracy Framework for Vehicle Dynamic Modeling in Autonomous Driving
The Reasonable Crowd Towards Evidence-Based and Interpretable Models of Driving Behavior
备注：感谢微信公众号「3D视觉工坊」整理。
Multi robot system:Cooperative Transportation Robot System Using Risk-Sensitive Stochastic Control
Others:Agent-Aware State Estimation for Autonomous Vehicles
Dynamic Lambda-Field A Counterpart of the Bayesian Occupancy Grid for Risk Assessment in Dynamic Environments
Finding Failures in High-Fidelity Simulation Using Adaptive Stress Testing and the Backward Algorithm
Gridlock-Free Autonomous Parking Lots for Autonomous Vehicles
StyleLess Layer Improving Robustness for Real-World Driving
Vehicle Dispatch in On-Demand Ride-Sharing with Stochastic Travel Times
Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization
本文仅做学术分享，如有侵权，请联系删文。
3D视觉精品课程推荐：
1.面向自动驾驶领域的多传感器数据融合技术
2.面向自动驾驶领域的3D点云目标检测全栈学习路线！(单模态+多模态/数据+代码) 3.彻底搞透视觉三维重建：原理剖析、代码讲解、及优化改进 4.国内首个面向工业级实战的点云处理课程 5.激光-视觉-IMU-GPS融合SLAM算法梳理和代码讲解 6.彻底搞懂视觉-惯性SLAM：基于VINS-Fusion正式开课啦 7.彻底搞懂基于LOAM框架的3D激光SLAM: 源码剖析到算法优化 8.彻底剖析室内、室外激光SLAM关键算法原理、代码和实战(cartographer+LOAM +LIO-SAM)
9.从零搭建一套结构光3D重建系统[理论+源码+实践]
10.单目深度估计方法：算法梳理与代码实现
重磅！3DCVer-学术论文写作投稿 交流群已成立
扫码添加小助手微信，可申请加入3D视觉工坊-学术论文写作与投稿 微信交流群，旨在交流顶会、顶刊、SCI、EI等写作与投稿事宜。
同时也可申请加入我们的细分方向交流群，目前主要有3D视觉、CV&深度学习、SLAM、三维重建、点云后处理、自动驾驶、多传感器融合、CV入门、三维测量、VR/AR、3D人脸识别、医疗影像、缺陷检测、行人重识别、目标跟踪、视觉产品落地、视觉竞赛、车牌识别、硬件选型、学术交流、求职交流、ORB-SLAM系列源码交流、深度估计等微信群。
一定要备注：研究方向+学校/公司+昵称，例如：”3D视觉 + 上海交大 + 静静“。请按照格式备注，可快速被通过且邀请进群。原创投稿也请联系。
▲长按加微信群或投稿
▲长按关注公众号
3D视觉从入门到精通知识星球：针对3D视觉领域的视频课程（三维重建系列、三维点云系列、结构光系列、手眼标定、相机标定、激光/视觉SLAM、自动驾驶等）、知识点汇总、入门进阶学习路线、最新paper分享、疑问解答五个方面进行深耕，更有各类大厂的算法工程人员进行技术指导。与此同时，星球将联合知名企业发布3D视觉相关算法开发岗位以及项目对接信息，打造成集技术与就业为一体的铁杆粉丝聚集区，近4000星球成员为创造更好的AI世界共同进步，知识星球入口：
学习3D视觉核心技术，扫描查看介绍，3天内无条件退款
圈里有高质量教程资料、答疑解惑、助你高效解决问题
觉得有用，麻烦给个赞和在看~
