自动驾驶

HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors

HGeo-TopoMap：利用分层几何先验增强拓扑映射

Siyu Li, Kunyu Peng, Di Wen, Beiping Hou, Zhiyong Li, Kailun Yang

机构 * Zhejiang University of Science and Technology（浙江科技学院） ； Hunan University（湖南大学） ； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） 纠错

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

AI总结 针对现实环境中心线检测难题，提出HGeo-TopoMap，利用显式先验地图和隐式空间关系，设计几何自适应和一致性学习模块增强拓扑映射，在OpenLane-V2数据集上评估，提高了精度与鲁棒性，优于基线方法。

Comments The source code and model weights will be made publicly available at https://github.com/lynn-yu/HGeo-TopoMap

RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots

仅RGB的主动3D场景图生成用于室内移动机器人

Giorgia Modi, Davide Buoso, Giuseppe Averta, Daniele De Martini

机构 * Mobile Robotics Group (MRG)（移动机器人小组） ； Visual and Multimodal Applied Learning Lab (VANDAL)（视觉与多模态应用学习实验室） 纠错

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

AI总结 本文提出了一种仅使用RGB输入的主动3D场景图生成方法，通过统一感知与规划的结构化表示，解决了传统方法对专用传感器的依赖问题，并在Replica数据集上验证了其有效性。

Hallucinating 360°: Panoramic Street-View Generation via Local Scenes Diffusion and Probabilistic Prompting

生成360°全景图：通过局部场景扩散与概率提示的街道视图生成

Fei Teng, Kai Luo, Sheng Wu, Siyu Li, Pujun Guo, Jiale Wei, Jiaming Zhang, Kunyu Peng, Kailun Yang

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） ； Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology（人机学与机器人研究所，卡尔斯鲁厄技术大学） 纠错

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

AI总结 本文提出Percep360方法，通过局部场景扩散与概率提示技术，实现自动驾驶中的可控全景图像生成，提升真实场景下的鸟瞰图分割性能。

Comments Accepted to ICRA 2026. The source code will be publicly available at https://github.com/FeiT-FeiTeng/Percep360

CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception

CoBEVMoE：基于动态专家混合的异质性感知特征融合

Lingzhao Kong, Jiacheng Lin, Siyu Li, Kai Luo, Zhiyong Li, Kailun Yang

机构 * School of Computer Science and Electronic Engineering, Hunan University（计算机科学与电子工程学院，湖南大学） ； School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学） ； National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（机器人视觉感知与控制技术国家工程研究中心，湖南大学） 纠错

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

AI总结 CoBEVMoE通过动态混合专家架构实现多智能体协作感知中的异质性特征融合，提升感知精度与性能。

Comments Accepted to ICRA 2026. The source code will be made publicly available at https://github.com/godk0509/CoBEVMoE

LLM4Laser: Large Language Models Automate the Design of Lasers

LLM4Laser: 利用大语言模型自动化激光器设计

Renjie Li, Ceyao Zhang, Sixuan Mao, Xiyuan Zhou, Feng Yin, Sergios Theodoridis, Zhaoyu Zhang

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

AI总结 本文提出利用大语言模型实现激光器设计自动化，通过对话生成仿真和强化学习代码，实现从概念到算法的全流程自动化设计。

Comments 14 pages, 10 figures

RG-Attn: Radian Glue Attention for Multi-modality Multi-agent Cooperative Perception

Lantao Li, Kang Yang, Wenqi Zhang, Xiaoxue Wang, Chen Sun

机构 * Sony (China) Limited（索尼（中国）有限公司） ； Renmin University of China（中国人民大学） 纠错

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

Comments Accepted by ICCV 2025 DriveX workshop (Final Version)

Visual SLAMMOT Considering Multiple Motion Models

Peilin Tian, Hao Li

机构 * Department of Automation, Shanghai Jiao Tong University（自动化系，上海交通大学） ； École d’Ingénieurs Paris SJTU (SPEIT)（巴黎工程学院SJTU（SPEIT）） 纠错

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

KDMOS:Knowledge Distillation for Motion Segmentation

Chunyu Cao, Jintao Cheng, Zeyu Chen, Linfan Zhan, Rui Fan, Zhijian He, Xiaoyu Tang

机构 * School of Electronic and Information Engineering, South China Normal University（南方科技大学电子与信息工程学院） ； College of Electronics & Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, the State Key Laboratory of Intelligent Autonomous Systems, and Frontiers Science Center for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究院、智能自主系统国家重点实验室及前沿科学中心，同济大学电子与信息工程学院） ； College of Big Data and Internet, Shenzhen Technology University（深圳技术大学大数据与互联网学院） 纠错

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

CODEI: Resource-Efficient Task-Driven Co-Design of Perception and Decision Making for Mobile Robots Applied to Autonomous Vehicles

Dejan Milojevic, Gioele Zardini, Miriam Elser, Andrea Censi, Emilio Frazzoli

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

Comments 20 pages, 33 images, IEEE Transactions on Robotics

Journal ref 10.1109/TRO.2025.3552347

Depth-aware Fusion Method based on Image and 4D Radar Spectrum for 3D Object Detection

Yue Sun, Yeqiang Qian, Chunxiang Wang, Ming Yang

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

Journal ref The 2024 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2024)

STAMP: Scalable Task And Model-agnostic Collaborative Perception

Xiangbo Gao, Runsheng Xu, Jiachen Li, Ziran Wang, Zhiwen Fan, Zhengzhong Tu

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

Comments Paper is accepted by ICLR 2025

HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection

Zijian Gu, Jianwei Ma, Yan Huang, Honghao Wei, Zhanye Chen, Hui Zhang, Wei Hong

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

Comments 12 pages, 8 figures, 7 tables. Accepted by AAAI 2025 , the 39th Annual AAAI Conference on Artificial Intelligence

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior

Sen Yang, Minyue Jiang, Ziwei Fan, Xiaolu Xie, Xiao Tan, Yingying Li, Errui Ding, Liang Wang, Jingdong Wang

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

Comments 17 pages, 7 figures, and 7 tables

AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer

Tanmoy Dam, Sanjay Bhargav Dharavath, Sameer Alam, Nimrod Lilith, Supriyo Chakraborty, Mir Feroskhan

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

Comments This paper has been accepted for ICRA 2024, and copyright will automatically transfer to IEEE upon its availability on the IEEE portal

Journal ref 2024 IEEE International Conference on Robotics and Automation (ICRA)

Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions

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

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

Comments 6 pages, 5 figures, 3 tables, accepted in IEEE International Conference on Intelligent Transportation Systems (ITSC) 2024

Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation

Mariella Dreissig, Simon Ruehle, Florian Piewak, Joschka Boedecker

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

DeTra: A Unified Model for Object Detection and Trajectory Forecasting

Sergio Casas, Ben Agro, Jiageng Mao, Thomas Gilles, Alexander Cui, Thomas Li, Raquel Urtasun

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

Automated Lane Change Behavior Prediction and Environmental Perception Based on SLAM Technology

Han Lei, Baoming Wang, Zuwei Shui, Peiyuan Yang, Penghao Liang

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

DeepIPC: Deeply Integrated Perception and Control for an Autonomous Vehicle in Real Environments

Oskar Natan, Jun Miura

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

Comments Accepted for Publication in IEEE Access

Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncoder

Xiaohao Xu

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

Sparse4D v3: Advancing End-to-End 3D Detection and Tracking

Xuewu Lin, Zixiang Pei, Tianwei Lin, Lichao Huang, Zhizhong Su

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

DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion

Jungwook Shin, Jaeill Kim, Kyungeun Lee, Hyunghun Cho, Wonjong Rhee

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

Freespace Optical Flow Modeling for Automated Driving

Yi Feng, Ruge Zhang, Jiayuan Du, Qijun Chen, Rui Fan

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

Comments This article has been accepted by IEEE/ASME Transactions on Mechatronics (T-Mech)

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Qiangeng Xu, Yiqi Zhong, Ulrich Neumann

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

Journal ref AAAI2022

VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction

Shubham Shrivastava

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

Comments Accepted at IJCAI 2021 Artificial Intelligence for Autonomous Driving Workshop

FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving

FIRE-VLA：面向自动驾驶的视觉-语言-动作模型的故障感知自演化

Hao Dou

机构 * Harbin Institute of Technology（哈尔滨工业大学） 纠错

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

AI总结 该研究针对自动驾驶VLA模型，提出FIRE-VLA故障感知自演化框架，结合GRPO与自蒸馏，在nuScenes数据集上降低了规划误差与故障流行率，提升了模型性能。

DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving

DVPSFormer：面向自动驾驶的高效在线深度感知视频全景分割

Yung-Hsu Yang, Luigi Piccinelli, Siyuan Li, Mattia Segu, Lei Ke, Martin Danelljan, Yuqian Fu, Zuria Bauer, Fisher Yu, Hermann Blum, Marc Pollefeys

机构 * ETH Zürich（苏黎世联邦理工学院） ； INSAIT, Sofia University（保加利亚索菲亚大学INSAIT研究所） ； University of Bonn（波恩大学） ； Microsoft（微软公司） 纠错

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

AI总结 DVPSFormer是一种统一在线架构，通过ESD和OMV机制实现高效4D场景理解，在两个DVPS基准上达SOTA，为自动驾驶提供在线机器人感知的精简方案。

A Real-Time Generalized Nash Equilibrium Framework for Interaction-Aware Autonomous Driving in Mixed Traffic

用于混合交通中交互感知自动驾驶的实时广义纳什均衡框架

Nouhed Naidja, Mohamed-Cherif Rahal, Steve Pechberti, Stéphane Font, Guillaume Sandou, Marc Revilloud

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

AI总结 针对自动驾驶在混合交通环境中的挑战，提出将驾驶交互建模为广义纳什均衡问题的决策框架，基于粒子群优化提出实时求解器，经实验验证能处理关键场景，求解器操作可行且收敛快。

Journal ref The 12th 2026 International Conference on Control, Decision and Information Technologies (CoDIT 2026), Jul 2026, Bari (Italy), Italy

PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving

PerceptDrive：用于端到端自动驾驶的具有自适应专家路由的感知先验世界-动作建模

Yushan Liu, Tianxiong Lv, Bohua Wang, Hangqi Fan, Chenxu Zhao, He Zheng, Xuchang Zhong, Yifan Xie, Congyang Zhao, Zhihao Liao, Leigang Luo, Yang Cai, Xiao-Ping Zhang, Wenbo Ding

机构 * Tsinghua University（清华大学） ； AMap, Alibaba Group（高德软件有限公司，阿里巴巴集团） 纠错

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

AI总结 研究针对自动驾驶中感知基础模型的问题，提出PerceptDrive框架，将教师提炼先验和观察潜变量输入可训练模型，经特定分支处理、先验保留及场景条件路由，实验表明其性能领先，证实相关方法的有效性及对先验的依赖。

Plug-and-Play Reweighting for Resilient Collaborative Decision-Making in Connected Autonomous Driving

用于联网自动驾驶中弹性协作决策的即插即用重加权方法

Jiewen Liu, Rui Liu, Matthew Lee, Ming C. Lin, Xiaorui Liu, Peng Gao

机构 * North Carolina State University（北卡罗来纳州立大学） ； University of Maryland, College Park（马里兰大学帕克分校） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

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

AI总结 针对联网自动驾驶中协作决策受感知噪声和对抗攻击影响的问题，提出弹性协作决策（RCDM）框架，含基于注意力的编解码器，设计即插即用重加权模块，经高保真模拟评估，性能优于现有方法，实现最优弹性能。

Comments 8 pages, 4 figures, 2 tables. Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)