自动驾驶

Open-World Active Learning with Stacking Ensemble for Self-Driving Cars

Paulo R. Vieira, Pedro D. Félix, Luis Macedo

专题命中 感知 ：self-driving(title)；分类 cs.CV

Ensemble-based Semi-supervised Learning to Improve Noisy Soiling Annotations in Autonomous Driving

Michal Uricar, Ganesh Sistu, Lucie Yahiaoui, Senthil Yogamani

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments Accepted for Oral Presentation at IEEE Intelligent Transportation Systems Conference (ITSC) 2021

Self-driving car safety quantification via component-level analysis

Juozas Vaicenavicius, Tilo Wiklund, Austė Grigaitė, Antanas Kalkauskas, Ignas Vysniauskas, Steven Keen

专题命中 感知 ：self-driving(title)；分类 cs.AI

Comments Various minor linguistic, typographical, and notational improvements. To appear in the SAE International Journal of Connected and Automated Vehicles, 4(1):2021, doi:10.4271/12-04-01-0004

Journal ref SAE Intl. J CAV 4(1):35-45, 2021

Preprocessing Methods of Lane Detection and Tracking for Autonomous Driving

Akram Heidarizadeh

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems

Clément Playout, Ola Ahmad, Freddy Lecue, Farida Cheriet

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments 10 pages, 4 figures

Non-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving

Min Bai, Shenlong Wang, Kelvin Wong, Ersin Yumer, Raquel Urtasun

专题命中 感知 ：self-driving(title)；分类 cs.CV

Computer Stereo Vision for Autonomous Driving

Rui Fan, Li Wang, Mohammud Junaid Bocus, Ioannis Pitas

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments Book chapter

Robust and Accurate Object Velocity Detection by Stereo Camera for Autonomous Driving

Toru Saito, Toshimi Okubo, Naoki Takahashi

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Journal ref IEEE Intelligent Vehicles Symposium, 2020

Bandwidth-Adaptive Feature Sharing for Cooperative LIDAR Object Detection

Ehsan Emad Marvasti, Arash Raftari, Amir Emad Marvasti, Yaser P. Fallah

专题命中 感知 ：LiDAR(title)；分类 cs.CV

Comments 8 pages, 4 figures, 2 table, 2020 IEEE 3rd Connected and Automated Vehicles Symposium: IEEE CAVS 2020

Edge Network-Assisted Real-Time Object Detection Framework for Autonomous Driving

Seung Wook Kim, Keunsoo Ko, Haneul Ko, Victor C. M. Leung

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments This paper will be published in IEEE Network

Weakly Supervised 3D Object Detection from Lidar Point Cloud

Qinghao Meng, Wenguan Wang, Tianfei Zhou, Jianbing Shen, Luc Van Gool, Dengxin Dai

专题命中 感知 ：LiDAR(title)；分类 cs.CV

Comments ECCV 2020; website: https://github.com/hlesmqh/WS3D

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

Jun Wang, Shiyi Lan, Mingfei Gao, Larry S. Davis

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars

Ran Emuna, Avinoam Borowsky, Armin Biess

专题命中 感知 ：self-driving(title)；分类 cs.RO

Optical Flow based Visual Potential Field for Autonomous Driving

Linda Capito, Keith Redmill, Umit Ozguner

专题命中 感知 ：autonomous driving(title)；分类 cs.RO

Comments This paper was accepted in the 31st IEEE Intelligent Vehicles Symposium (IV2020)

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

Ekim Yurtsever, Jacob Lambert, Alexander Carballo, Kazuya Takeda

专题命中 感知 ：autonomous driving(title)；分类 cs.RO

Comments 26 pages, 15 figures. Published in IEEE Access

Journal ref IEEE Access, volume 8. 2020

Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks

Ehsan Emad Marvasti, Arash Raftari, Amir Emad Marvasti, Yaser P. Fallah, Rui Guo, HongSheng Lu

专题命中 感知 ：LiDAR(title)；分类 cs.CV

Comments 7 pages, 6 figures

Universally Safe Swerve Manoeuvres for Autonomous Driving

Ryan De Iaco, Stephen L. Smith, Krzysztof Czarnecki

专题命中 感知 ：autonomous driving(title)；分类 cs.RO

Real-time 3D Traffic Cone Detection for Autonomous Driving

Ankit Dhall, Dengxin Dai, Luc Van Gool

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments IEEE Intelligent Vehicles Symposium (IV'19). arXiv admin note: text overlap with arXiv:1809.10548

Rethinking Self-driving: Multi-task Knowledge for Better Generalization and Accident Explanation Ability

Zhihao Li, Toshiyuki Motoyoshi, Kazuma Sasaki, Tetsuya Ogata, Shigeki Sugano

专题命中 感知 ：self-driving(title)；分类 cs.CV

Comments 11 pages, 4 figures, 3 tables

Social Cohesion in Autonomous Driving

Nicholas C. Landolfi, Anca D. Dragan

专题命中 感知 ：autonomous driving(title)；分类 cs.RO

GPU-based Pedestrian Detection for Autonomous Driving

Victor Campmany, Sergio Silva, Antonio Espinosa, Juan Carlos Moure, David Vázquez, Antonio M. López

专题命中 感知 ：autonomous driving(title)；分类 cs.CV

Comments 10 pages

Journal ref International Conference on Computational Science 2016 Volume 80 Pages 2377 to 2381

RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning

RISE：跨三维跟踪与结构化视觉-语言推理的路边基础设施序列理解

Yanbo Jiang, Haotian Zheng, Jiahao Wang, Hanxiao Ren, Yitao Xu, Yining Xing, Zehong Ke, Hao Cheng, Yiqian Tu, Jinhao Li, Zhiyuan Xuan, Fang Zhang, Jianqiang Wang

专题命中 感知 ：LiDAR(abstract,abstract_cn)；分类 cs.CV、cs.AI

AI总结 本研究提出RISE框架，结合仅图像的三维跟踪方法与结构化视觉-语言推理，构建含33910个问答对的RISE-VQA数据集，通过RISE-Bench评估任务，揭示相关挑战并验证域自适应与时间上下文的益处。

ATLASFusion: Aggregation Tracking with Location-Aware Sparse Fusion for Robust Spatio-Temporal Multi-View Pedestrian Tracking

ATLASFusion：用于鲁棒时空多视角行人跟踪的位置感知稀疏融合聚合跟踪

Keisuke Toida, Taigo Sakai, Takeshi Nakamura, Hiroshi Shimizu, Kazuhiro Hotta

机构 * Meijo University（名古屋大学） ； Chubu Electric Power Co., Inc.（Chubu电力公司） 纠错

专题命中 感知 ：BEV(abstract,abstract_cn)；分类 cs.CV、cs.AI

AI总结 本文提出ATLASFusion框架，通过稀疏透视变换、密度感知加权聚合等技术解决多视角行人跟踪的特征畸变问题，在基准测试中提升精度与鲁棒性，且计算开销极小。

HeteroPROPMT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework

HeteroPROPMT：一种实时且隐私保护的异构协同感知框架

Armin Maleki, Hayder Radha

机构 * Michigan State University（密歇根州立大学） 纠错

专题命中 感知 ：BEV(abstract,abstract_cn)；分类 cs.RO、cs.CV

AI总结 HeteroPROPMT是一种实时隐私保护异构协同感知框架，通过模块化提示与轻量调优对齐异构智能体特征，在OPV2V-H等数据集上性能优于现有方法，且参数效率高、隐私性好。

Comments Accepted to 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 9 pages, 4 figures, 5 tables

Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning

测试时覆盖：用于部署感知学习的测试条件数据管理

Nadine Chang, Maying Shen, Shizhe Diao, Jialiang Wang, Jingde Chen, Thomas Breuel, Pavlo Molchanov, Rafid Mahmood, Jose M. Alvarez

机构 * NVIDIA（英伟达） ； University of Ottawa（渥太华大学） 纠错

专题命中 感知 ：autonomous driving(abstract)；end-to-end driving(abstract)；分类 cs.CV、cs.AI

AI总结 研究针对部署的AI系统训练需数据管理的问题，提出TTCov方法，通过构建任务图谱和知识图谱分别表示覆盖与分布，选择预算训练集，应用于自动驾驶时能提升数据质量及性能，实现对新领域的无缝适应。

PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion

PGTT：用于感知式有腿运动的相位引导地形遍历

Alexandros Ntagkas, Chairi Kiourt, Konstantinos Chatzilygeroudis

机构 * Laboratory of Automation and Robotics (LAR) in the Department of Electrical & Computer Engineering, University of Patras（自动化与机器人实验室（LAR）（电气与计算机工程系，帕特拉斯大学）） ； Archimedes/Athena RC, Greece（阿基米德/雅典娜RC，希腊） ； Athena - Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece（雅典娜信息、通信和知识技术研究中心（Xanthi，希腊）） ； Computational Intelligence Laboratory (CILab), Department of Mathematics, University of Patras（计算智能实验室（CILab）（数学系，帕特拉斯大学）） 纠错

专题命中 感知 ：LiDAR(abstract,abstract_cn)；分类 cs.RO、cs.AI

AI总结 研究针对有腿机器人感知强化学习控制器的不足，提出相位引导地形遍历（PGTT）方法，通过奖励塑造强化步态结构，编码腿相位等，在特定训练下，该方法在多种场景成功率高且速度跟踪可比，还能跨平台转移。

Comments 8 pages, 9 figures, 3 tables, Accepted at IROS 2026

CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement

CoGoal3D：基于3D感知融合与优化的协作式3D目标检测

Zhihao Yang, Zhiyu Xiang, Peng Xu, Tianyu Pu, Kai Wang, Eryun Liu, Dongping Zhang, Yong Ding

机构 * Zhejiang University（浙江大学） ； Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing（浙江省多模态通信网络与智能信息处理重点实验室） ； China Jiliang University（中国计量大学） 纠错

专题命中 感知 ：BEV(abstract,abstract_cn)；分类 cs.CV、cs.AI

AI总结 针对V2X协作目标检测中3D检测效果不佳的问题，提出CoGoal3D框架，通过两阶段管道提取和优化3D特征，设计融合模块与辅助任务，还提出数据增强策略，在多数据集上取得新的最优性能。

Comments Accepted to ECCV 2026. 17 pages, 8 figures, 6 tables. Code: https://github.com/Megalo-f/CoGoal3D

Hydra++: Real-Time Hierarchical 3D Scene Graph Construction With Object-Level Shape Estimation

Hydra++：通过对象级形状估计进行实时分层3D场景图构建

Hyungtae Lim, Nathan Hughes, Xihang Yu, Ruihan Xu, Yun Chang, Jingnan Shi, Rajat Talak, Luca Carlone

机构 * Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（信息与决策系统实验室，麻省理工学院） 纠错

专题命中 感知 ：LiDAR(abstract,abstract_cn)；分类 cs.RO、cs.CV

AI总结 研究如何将基于学习的对象形状估计器集成到分层3D场景图管道中，提出Hydra++系统。它结合形状估计和一致性检查，默认配置可在线构建场景图，支持混合配置应对室外挑战，实验证明其提高了对象和场景级重建质量。

Comments 8 pages, 12 figures, accepted in Proc. IEEE/RSJ IROS

OctoSense: Self-Supervised Learning for Multimodal Robot Perception

OctoSense: 多模态机器人感知的自监督学习

Anthony Bisulco, Jeremy Wang, Kostas Daniilidis, Randall Balestriero, Pratik Chaudhari

专题命中 感知 ：LiDAR(abstract,abstract_cn)；分类 cs.RO、cs.CV

AI总结 提出OctoSense传感器平台和数据集，通过“晚融合”掩码自编码器实现多模态自监督学习，在多种退化条件下鲁棒预测光流、深度、语义分割和自运动。

Unsupervised Memory-Enhanced Video Transformers: Obstacle Detection for Autonomous Agricultural Rover

无监督记忆增强视频变换器：自主农业机器人的障碍物检测

Théo Biardeau, Anne-Sophie Capelle-Laizé, Salwan Alwan, David Helbert

专题命中 感知 ：LiDAR(abstract,abstract_cn)；分类 cs.RO、cs.AI

AI总结 提出VMTAD，一种无监督方法，利用记忆增强的变换器处理动态场景，实现农业机器人实时障碍物检测，在油菜数据集上达到SOTA性能。

Journal ref Precision Agriculture, 2026, 27 (3), pp.74