自动驾驶 - arXivDaily 专题

2505.16985 2026-03-05 cs.CV cs.AI cs.LG cs.RO 67%

Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation

极简多模态异常合成用于分布外检测与分割

Moru Liu, Hao Dong, Jessica Kelly, Olga Fink, Mario Trapp

机构 * Technical University of Munich（慕尼黑技术大学）； ETH Zürich（苏黎世联邦理工学院）； Fraunhofer IKS（弗劳恩霍夫研究所）； EPFL（苏黎世联邦理工学院）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结本文提出极简多模态异常合成方法Feature Mixing，通过理论支持提升OOD检测性能，实验表明其在多个数据集上达到最优效果，速度提升显著。

Comments NeurIPS 2025

2512.05299 2026-02-03 eess.SY cs.AR cs.CV cs.ET cs.RO cs.SY eess.IV 67%

ARCAS: An Augmented Reality Collision Avoidance System with SLAM-Based Tracking for Enhancing VRU Safety

ARCAS：一种基于SLAM跟踪的增强现实避障系统，用于提升VRU安全

Ahmad Yehia, Jiseop Byeon, Tianyi Wang, Huihai Wang, Yiming Xu, Junfeng Jiao, Christian Claudel

机构 * Department of Civil, Architectural, and Environmental Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校土木、建筑与环境工程系）； School of Architecture, The University of Texas at Austin（德克萨斯大学奥斯汀分校建筑学院）

专题命中感知：LiDAR(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 ARCAS通过融合激光雷达与SLAM跟踪，为行人提供实时AR避障，显著提升城市出行安全。

Comments 8 pages, 3 figures, 1 table, accepted for IEEE Intelligent Vehicles (IV) Symposium 2026

2507.06978 2026-01-21 physics.optics 67%

Anti-Interference Diffractive Deep Neural Networks for Multi-Object Recognition

抗干扰衍射深度神经网络用于多目标识别

Zhiqi Huang, Yufei Liu, Nan Zhang, Zian Zhang, Qiming Liao, Cong He, Shendong Liu, Youhai Liu, Hongtao Wang, Xingdu Qiao, Joel K. W. Yang, Yan Zhang, Lingling Huang, Yongtian Wang

专题命中感知：autonomous driving(abstract)；driving perception(abstract)

AI总结本文提出抗干扰衍射深度神经网络，用于多目标识别，通过不同训练策略和物理网络实现高准确率分类。

Comments Complete manuscript, 28 pages, 13 figures

Journal ref Light: Science & Applications, 2026

2504.18419 2026-01-15 cs.CV cs.AI cs.RO 67%

A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detection

一种多模态混合后期级联融合网络用于增强的3D物体检测

Carlo Sgaravatti, Roberto Basla, Riccardo Pieroni, Matteo Corno, Sergio M. Savaresi, Luca Magri, Giacomo Boracchi

机构 * Politecnico di Milano（米兰理工学院）

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

AI总结本文提出了一种多模态混合后期级联融合网络，通过结合RGB和3D激光雷达检测器，提升3D物体检测的性能，特别是在行人和自行车检测方面表现优异。

2502.10975 2025-12-30 cs.RO cs.CV eess.IV 67%

GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting

GS-GVINS: 一种集成GNSS-视觉-惯性导航系统的系统，结合3D高斯点分布

Zelin Zhou, Saurav Uprety, Shichuang Nie, Hongzhou Yang

机构 * Department of Geomatics Engineering, Shulich School of Engineering, University of Calgary（测绘工程系、谢里尔工程学院、卡尔加里大学）

专题命中感知：LiDAR(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 GS-GVINS是一种结合3D高斯点分布的GNSS-视觉-惯性导航系统，通过提升导航精度实现大规模户外导航。

2505.03539 2025-12-12 cs.CV cs.RO eess.IV 67%

Panoramic Out-of-Distribution Segmentation

全景异常检测分割

Mengfei Duan, Yuheng Zhang, Yihong Cao, Fei Teng, Kai Luo, Jiaming Zhang, Kailun Yang, Zhiyong Li

机构 * School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（人工智能与机器人学院和机器人视觉感知与控制技术国家工程研究中心，湖南大学）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结本文提出全景异常检测分割任务及POS方法，通过文本引导的提示分布学习提升全景图像的异常检测与分割性能。

Comments Code and datasets will be available at https://github.com/MengfeiD/PanOoS

2503.02687 2025-11-20 cs.CV cs.AI cs.LG cs.RO 67%

Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?

Miao Zhang, Sherif Abdulatif, Benedikt Loesch, Marco Altmann, Bin Yang

机构 * Robert Bosch GmbH, Corporate Research（罗伯特·博世有限公司，企业研究）； University of Stuttgart, Institute of Signal Processing and System Theory（斯图加特大学，信号处理与系统理论研究所）

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

Comments 8 pages, 6 figures, 4 tables, accepted to 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025). Code: https://github.com/boschresearch/CAPMIX

2511.08615 2025-11-13 cs.CV cs.IT cs.LG cs.RO eess.IV math.IT 67%

A Multi-Drone Multi-View Dataset and Deep Learning Framework for Pedestrian Detection and Tracking

Kosta Dakic, Kanchana Thilakarathna, Rodrigo N. Calheiros, Teng Joon Lim

专题命中感知：BEV(abstract)；分类 cs.RO、cs.CV、eess.IV

Comments Introduction of the MATRIX Dataset, featuring synchronized footage from eight drones in an urban environment with comprehensive annotations for detection and tracking, available at https://github.com/KostaDakic/MATRIX/tree/main

2511.05982 2025-11-11 cs.CV cs.AI cs.LG cs.RO 67%

Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey

Albert Schotschneider, Svetlana Pavlitska, J. Marius Zöllner

机构 * Institute for Applied Informatics and Formal Description Methods（应用信息学与形式描述方法研究所）； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments 6 pages, 1 figure, 2 tables, accepted at IEEE SMC 2025 in Vienna, presented on 8th October 2025

2510.22370 2025-10-28 cs.RO cs.AI cs.CV cs.LG cs.SE 67%

BLIP-FusePPO: A Vision-Language Deep Reinforcement Learning Framework for Lane Keeping in Autonomous Vehicles

Seyed Ahmad Hosseini Miangoleh, Amin Jalal Aghdasian, Farzaneh Abdollahi

机构 * Department of Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic)（电气工程系，阿米尔卡比尔技术大学（德黑兰理工大学））

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

Comments https://github.com/Amin-A96/BLIP-FusePPO-A-Vision-Language-Deep-Reinforcement-Learning-Framework-for-Lane-Keeping-in-Autonomous.git

2510.19001 2025-10-23 cs.CV cs.AI cs.RO 67%

Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts

Seungjun Yu, Junsung Park, Youngsun Lim, Hyunjung Shim

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

2510.14293 2025-10-17 cs.RO cs.AI cs.CV cs.LG 67%

Learning Human-Humanoid Coordination for Collaborative Object Carrying

Yushi Du, Yixuan Li, Baoxiong Jia, Yutang Lin, Pei Zhou, Wei Liang, Yanchao Yang, Siyuan Huang

机构 * Department of Electrical and Electronic Engineering, the University of Hong Kong（香港大学电子与电气工程系）； State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）； School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）； Yuanpei College, Peking University（北京大学元培学院）

专题命中感知：trajectory planning(abstract)；分类 cs.RO、cs.CV、cs.AI

2510.09945 2025-10-14 cs.CV cs.AI cs.HC cs.LG eess.IV 67%

Explainable Human-in-the-Loop Segmentation via Critic Feedback Signals

Pouya Shaeri, Ryan T. Woo, Yasaman Mohammadpour, Ariane Middel

机构 * Arizona State University（亚利桑那州立大学）

专题命中感知：autonomous driving(abstract)；分类 cs.CV、eess.IV、cs.AI

Comments Submitted to a computer vision conference (under review)

2509.20107 2025-09-26 cs.CV cs.AI cs.LG cs.RO 67%

Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models

Juana Valeria Hurtado, Rohit Mohan, Abhinav Valada

机构 * Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系）； Baden-Württemberg Stiftung gGmbH（巴登-符腾堡基金会）； Bosch Research（博世研究）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

2506.06474 2025-09-25 cs.RO cs.AI cs.CV cs.MA cs.NI 67%

Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception

Everett Richards, Bipul Thapa, Lena Mashayekhy

机构 * San Diego State University（圣地亚哥州立大学）； University of Delaware（特拉华大学）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments This paper has been accepted to IEEE EDGE 2025. The final version will be published in IEEE Xplore later this year

2509.03462 2025-09-04 cs.AI cs.CV cs.RO 67%

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning

Zhuo Cao, Yunxiao Shi, Min Xu

机构 * University of Queensland, School of Civil Engineering（昆士兰大学土木工程学院）； University of Technology Sydney, Faculty of Engineering（悉尼科技大学工程学院）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments 5 pages

2508.00299 2025-08-04 cs.CV cs.AI cs.RO 67%

Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence

Danzhen Fu, Jiagao Hu, Daiguo Zhou, Fei Wang, Zepeng Wang, Wenhua Liao

机构 * MiLM Plus, Xiaomi Inc.（小米公司）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments ICCV 2025 Workshop (HiGen)

2504.05119 2025-07-23 cs.LG cs.AI cs.AR cs.CV eess.IV 67%

Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection

Jon Gutiérrez-Zaballa, Koldo Basterretxea, Javier Echanobe

机构 * Department of Electronics Technology, University of the Basque Country (UPV/EHU)（电子技术系，巴斯克国家大学（UPV/EHU））； Department of Electricity and Electronics, University of the Basque Country (UPV/EHU)（电力与电子系，巴斯克国家大学（UPV/EHU））

专题命中感知：autonomous driving(abstract)；分类 cs.CV、eess.IV、cs.AI

2506.19283 2025-07-04 cs.CV cs.AI cs.RO 67%

AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration

Xiangbo Gao, Yuheng Wu, Fengze Yang, Xuewen Luo, Keshu Wu, Xinghao Chen, Yuping Wang, Chenxi Liu, Yang Zhou, Zhengzhong Tu

机构 * Texas A&M University（德克萨斯理工大学）； KAIST（韩国科学技术院）； The University of Utah（犹他大学）； University of Washington（华盛顿大学）； University of Michigan（密歇根大学）

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

2503.13504 2025-07-02 cs.LG cs.AI cs.CV cs.RO 67%

CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception

Rujia Wang, Xiangbo Gao, Hao Xiang, Runsheng Xu, Zhengzhong Tu

机构 * Computer Science and Engineering, Texas A&M University（计算机科学与工程，德克萨斯A&M大学）； University of California, Los Angeles（加州大学洛杉矶分校）

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

2506.22593 2025-07-01 cs.RO cs.AI cs.CV 67%

Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding

Antonello Longo, Chanyoung Chung, Matteo Palieri, Sung-Kyun Kim, Ali Agha, Cataldo Guaragnella, Shehryar Khattak

机构 * NASA Jet Propulsion Laboratory, California Institute of Technology（美国国家航空航天局喷气推进实验室、加州理工学院）； Department of Electrical And Information Engineering, Polytechnic University of Bari（巴里理工学院电子与信息工程系）； Field AI

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

Comments Paper accepted to 2025 IEEE International Conference on Automation Science and Engineering (CASE)

2506.20597 2025-06-26 eess.SP 67%

Differential Transformer-driven 6G Physical Layer for Collaborative Perception Enhancement

Soheyb Ribouh, Osama Saleem, Mohamed Ababsa

专题命中感知：autonomous driving(abstract)；LiDAR(abstract)

2406.06967 2025-06-23 cs.CV cs.AI eess.IV 67%

Dual Thinking and Logical Processing -- Are Multi-modal Large Language Models Closing the Gap with Human Vision ?

Kailas Dayanandan, Nikhil Kumar, Anand Sinha, Brejesh Lall

机构 * Indian Institute of Technology Delhi（印度理工学院德里）

专题命中感知：autonomous driving(abstract)；分类 cs.CV、eess.IV、cs.AI

2506.13505 2025-06-17 eess.IV cs.AI cs.ET cs.RO 67%

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data

Vasiliki Balaska, Ioannis Tsampikos Papapetros, Katerina Maria Oikonomou, Loukas Bampis, Antonios Gasteratos

机构 * Department of Production and Management Engineering, Democritus University of Thrace（生产与管理工程系，德米特里乌斯·特拉基斯大学）； Department of Electrical and Computer Engineering, Democritus University of Thrace（电气与计算机工程系，德米特里乌斯·特拉基斯大学）

专题命中感知：LiDAR(abstract)；分类 cs.RO、eess.IV、cs.AI

2504.12817 2025-04-18 cs.RO cs.AI cs.CV 67%

Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks

Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Workshop "Advancing Automated Driving in Highly Interactive Scenarios through Behavior Prediction, Trustworthy AI, and Remote Operations" @ 36th IEEE Intelligent Vehicles Symposium (IV)

2411.02624 2025-04-07 cs.CV cs.AI cs.RO 67%

Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach

Minghao Ning, Yaodong Cui, Yufeng Yang, Shucheng Huang, Zhenan Liu, Ahmad Reza Alghooneh, Ehsan Hashemi, Amir Khajepour

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

Journal ref 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)

2503.06170 2025-03-13 cs.AI cs.CV cs.RO 67%

Object-Centric World Model for Language-Guided Manipulation

Youngjoon Jeong, Junha Chun, Soonwoo Cha, Taesup Kim

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

2203.13310 2025-02-14 cs.CV cs.AI eess.IV 67%

MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection

Renrui Zhang, Han Qiu, Tai Wang, Ziyu Guo, Yiwen Tang, Xuanzhuo Xu, Ziteng Cui, Yu Qiao, Peng Gao, Hongsheng Li

专题命中感知：autonomous driving(abstract)；分类 cs.CV、eess.IV、cs.AI

Comments Accepted by ICCV 2023. Code is available at https://github.com/ZrrSkywalker/MonoDETR

2502.02334 2025-02-05 cs.CV cs.RO eess.IV 67%

Event-aided Semantic Scene Completion

Shangwei Guo, Hao Shi, Song Wang, Xiaoting Yin, Kailun Yang, Kaiwei Wang

专题命中感知：autonomous driving(abstract)；分类 cs.RO、cs.CV、eess.IV

Comments The established datasets and codebase will be made publicly at https://github.com/Pandapan01/EvSSC

2501.07808 2025-01-15 cs.AI cs.CV eess.IV 67%

A Low-cost and Ultra-lightweight Binary Neural Network for Traffic Signal Recognition

Mingke Xiao, Yue Su, Liang Yu, Guanglong Qu, Yutong Jia, Yukuan Chang, Xu Zhang

专题命中感知：autonomous driving(abstract)；分类 cs.CV、eess.IV、cs.AI

1. 感知 6059 篇

Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation

ARCAS: An Augmented Reality Collision Avoidance System with SLAM-Based Tracking for Enhancing VRU Safety

Anti-Interference Diffractive Deep Neural Networks for Multi-Object Recognition

A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detection

GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting

Panoramic Out-of-Distribution Segmentation

Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?

A Multi-Drone Multi-View Dataset and Deep Learning Framework for Pedestrian Detection and Tracking

Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey

BLIP-FusePPO: A Vision-Language Deep Reinforcement Learning Framework for Lane Keeping in Autonomous Vehicles

Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts

Learning Human-Humanoid Coordination for Collaborative Object Carrying

Explainable Human-in-the-Loop Segmentation via Critic Feedback Signals

Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models

Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning

Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence

Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection

AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration

CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception

Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding

Differential Transformer-driven 6G Physical Layer for Collaborative Perception Enhancement

Dual Thinking and Logical Processing -- Are Multi-modal Large Language Models Closing the Gap with Human Vision ?

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data

Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks

Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach

Object-Centric World Model for Language-Guided Manipulation

MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection

Event-aided Semantic Scene Completion

A Low-cost and Ultra-lightweight Binary Neural Network for Traffic Signal Recognition