自动驾驶 - arXivDaily 专题

1809.05590 2019-05-07 cs.RO 83%

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection

Di Feng, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.RO

Comments 30th IEEE Intelligent Vehicles Symposium

1903.03669 2019-03-12 cs.RO 83%

Recognizing and Tracking High-Level, Human-Meaningful Navigation Features of Occupancy Grid Maps

Payam Nikdel, Richard Vaughan

专题命中感知：occupancy(title,abstract)；LiDAR(abstract)；分类 cs.RO

Comments Video: https://youtu.be/zNnsH9tNUNU

1709.05581 2019-01-15 cs.LG cs.RO 83%

MultiNet: Multi-Modal Multi-Task Learning for Autonomous Driving

Sauhaarda Chowdhuri, Tushar Pankaj, Karl Zipser

专题命中感知：autonomous driving(title,abstract)；self-driving(abstract)；分类 cs.RO

Comments Published in IEEE WACV 2019

1810.12436 2018-10-31 cs.NE cs.AI 83%

Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks

Shibo Zhou, Wei Wang

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.AI

1809.06972 2018-09-20 cs.RO 83%

Mapless Online Detection of Dynamic Objects in 3D Lidar

David J. Yoon, Tim Y. Tang, Timothy D. Barfoot

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.RO

Comments 7 pages, 8 figures

1809.00426 2018-09-05 cs.RO 83%

Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learning

Jilin Mei, Biao Gao, Donghao Xu, Wen Yao, Xijun Zhao, Huijing Zhao

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.RO

1805.04902 2018-05-21 cs.CV 83%

LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR

Kazuki Minemura, Hengfui Liau, Abraham Monrroy, Shinpei Kato

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.CV

1711.06703 2018-02-15 cs.CV cs.LG 83%

Fusing Bird View LIDAR Point Cloud and Front View Camera Image for Deep Object Detection

Zining Wang, Wei Zhan, Masayoshi Tomizuka

专题命中感知：LiDAR(title,abstract)；autonomous driving(abstract)；分类 cs.CV

Comments 10 pages, 6 figures, 3 tables

1711.06459 2017-11-21 cs.CV 83%

Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Driving

Yiqi Hou, Sascha Hornauer, Karl Zipser

专题命中感知：autonomous driving(title,abstract)；end-to-end driving(abstract)；分类 cs.CV

Comments CVPR 2018 Submission, 9 pages, 6 figures, 3 tables

1708.04989 2017-08-17 cs.CV 83%

Free Space Estimation using Occupancy Grids and Dynamic Object Detection

Raghavender Sahdev

专题命中感知：occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.CV

Comments 10 pages, 10 figures

1611.07759 2017-06-23 cs.CV 83%

Multi-View 3D Object Detection Network for Autonomous Driving

Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia

专题命中感知：autonomous driving(title,abstract)；LiDAR(abstract)；分类 cs.CV

Comments To appear in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

1911.01054 2019-11-22 cs.CV cs.LG cs.RO eess.IV 83%

SoildNet: Soiling Degradation Detection in Autonomous Driving

Arindam Das

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

Comments Accepted at the NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving

1906.11873 2019-07-01 cs.CV cs.LG cs.RO eess.IV 83%

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

Hager Radi, Waleed Ali

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

Comments Accepted at Thirty-sixth International Conference on Machine Learning (ICML 2019) Workshop on AI for Autonomous Driving

2603.08199 2026-08-05 cs.CV cs.RO 版本更新 82%

Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object Tracking

Fusion-Poly: 一种基于时空融合的多边形框架用于3D多目标跟踪

Xian Wu, Yitao Wu, Xiaoyu Li, Zijia Li, Lijun Zhao, Lining Sun

机构 * State Key Laboratory of Robotics and System, Harbin Institute of Technology（机器人与系统国家重点实验室，哈尔滨工业大学）

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

AI总结 Fusion-Poly通过整合异步LiDAR和相机数据，提出一种时空融合框架，提升3D多目标跟踪的轨迹一致性与更新频率。

2604.13476 2026-04-28 cs.RO cs.CV 82%

RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception

RobotPan：一种用于具身感知的360度全景机器人视觉系统

Jiahao Ma, Qiang Zhang, Peiran Liu, Zeran Su, Pihai Sun, Gang Han, Wen Zhao, Wei Cui, Zhang Zhang, Zhiyuan Xu, Renjing Xu, Jian Tang, Miaomiao Liu, Yijie Guo

机构 * Tiangong 3.0 humanoid platform（天宫3.0人形平台）

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

AI总结本文提出RobotPan系统，通过六摄像头与LiDAR结合，实现360度全景视觉覆盖，采用统一球坐标表示和分层球体体素先验，实现高效实时渲染与重建，支持长时间序列处理，并发布多传感器数据集用于机器人导航与 manipulation。

Comments Project website: https://robotpan.github.io/

2604.14089 2026-04-16 cs.RO cs.AI 82%

UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception

UMI-3D：从视觉受限到3D空间感知的通用操作接口扩展

Ziming Wang

机构 * HKU（香港大学）； USTC（中国科学技术大学）

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

AI总结 UMI-3D通过集成轻量级低成本LiDAR传感器，提升数据采集的鲁棒性和可扩展性，实现3D空间感知，增强操作任务的性能与可行性。

2608.01035 2026-08-17 cs.RO cs.AI cs.CV 版本更新 82%

WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

WAM-Diff2：面向高效自动驾驶视觉-语言-动作（VLA）的分层自回归到扩散蒸馏

Zhihao Zhu, Hanlin Shang, Mingwang Xu, Feipeng Cai, Zhuolin He, Yaoyi Li, Jianhua Han, Hang Xu, Siyu Zhu

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

AI总结 WAM-Diff2通过三阶段分层蒸馏策略，将预训练自回归VLA模型转化为高效扩散模型，缓解暴露偏差、实现与基线相当性能，解码速度提升2.8倍，结合系统级优化后达15.1倍加速。

2601.08609 2026-07-14 cs.SE 82%

Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems

覆盖引导的道路选择与优先级分配以提高自动驾驶系统测试效率

Qurban Ali, Andrea Stocco, Leonardo Mariani, Oliviero Riganelli

专题命中感知：autonomous driving(title,abstract)；self-driving(abstract)

AI总结本文提出了一种覆盖引导的道路选择与优先级分配方法，通过减少冗余并保持多样性，提高自动驾驶系统测试效率，实现测试套件大小减少89%并提升故障检测能力95倍。

Comments The IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) 2026

2606.11889 2026-06-11 cs.CV cs.AI cs.RO 新提交 82%

Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection

面向自动驾驶危险检测的视觉-语言模型任务对齐稳定性分析

Everett Richards

机构 * Everett Richards（埃弗里特·里奇ards）

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

AI总结研究视觉-语言模型在自动驾驶危险检测中，嵌入漂移与任务对齐危险分数变化的关系，发现不同腐败类型导致不同的失效模式，建议基准测试包含任务对齐稳定性指标。

Comments 8 pages (5 main body + 3 references / appendices). ICML 2026 Workshop on Combining Theory and Benchmarks (CTB)

2601.14702 2026-05-27 cs.AI cs.CV cs.RO 82%

Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving

Drive-P2D：自动驾驶中视觉语言模型的渐进式感知到决策基准

Zecong Tang, Zixu Wang, Yifei Wang, Weitong Lian, Tianjian Gao, Haoran Li, Tengju Ru, Lingyi Meng, Zhejun Cui, Yichen Zhu, Qi Kang, Kaixuan Wang, Yu Zhang

机构 * Zhejiang University（浙江大学）； The University of Hong Kong（香港大学）

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

AI总结提出Drive-P2D基准，通过分离推理与答案的协议，在目标、场景和决策三个层级上评估视觉语言模型的感知到决策能力，并分析错误模式。

2507.09095 2026-03-09 cs.LG 82%

Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving

针对自动驾驶多模态感知的时序错位攻击

Md Hasan Shahriar, Md Mohaimin Al Barat, Harshavardhan Sundar, Ning Zhang, Naren Ramakrishnan, Y. Thomas Hou, Wenjing Lou

机构 * Amazon.com, Inc.（亚马逊公司）； Washington University in St. Louis（华盛顿大学）

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

AI总结本文提出DejaVu攻击，通过制造时序错位破坏自动驾驶多模态感知，导致目标检测和跟踪性能显著下降。

Comments 19 pages, 18 Figures

2504.13647 2026-02-25 cs.RO cs.AI cs.CV 82%

An Efficient LiDAR-Camera Fusion Network for Multi-Class 3D Dynamic Object Detection and Trajectory Prediction

一种高效的激光雷达-摄像头融合网络用于多类3D动态物体检测和轨迹预测

Yushen He, Lei Zhao, Tianchen Deng, Zipeng Fang, Weidong Chen

机构 * Institute of Medical Robotics and Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education（医学机器人研究所和自动化系，上海交通大学，系统控制与信息处理重点实验室，教育部）

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

AI总结本文提出了一种高效的激光雷达-摄像头融合网络，用于多类3D动态物体检测与轨迹预测，通过UniMT和RTMCT模型实现高精度检测与多样化轨迹预测。

2512.22244 2025-12-30 cs.SE cs.CR 82%

Failure Analysis of Safety Controllers in Autonomous Vehicles Under Object-Based LiDAR Attacks

基于目标的激光雷达攻击下自动驾驶车辆安全控制器失效分析

Daniyal Ganiuly, Nurzhau Bolatbek, Assel Smaiyl

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

AI总结本文研究基于目标的激光雷达攻击对自动驾驶车辆安全控制器的影响，揭示了感知鲁棒性与控制安全之间的差距，并为设计更安全的控制策略提供参考。

2405.15033 2025-11-17 cs.CV cs.AI eess.IV 82%

Fractured Glass, Failing Cameras: Simulating Physics-Based Adversarial Samples for Autonomous Driving Systems

Manav Prabhakar, Jwalandhar Girnar, Arpan Kusari

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

Comments Accepted to AAAI

2511.00060 2025-11-04 cs.CV cs.RO eess.IV 82%

Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?

Zhiqi Qi, Runxin Zhao, Hanyang Zhuang, Chunxiang Wang, Ming Yang

机构 * School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（自动化与智能感知学院，上海交通大学）； Global College, Shanghai Jiao Tong University（全球学院，上海交通大学）

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

2408.13653 2025-10-15 cs.SE 82%

On the Robustness Evaluation of 3D Obstacle Detection Against Specifications in Autonomous Driving

Tri Minh Triet Pham, Bo Yang, Jinqiu Yang

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

Comments 13 pages, accepted by ASE 2025

2507.23064 2025-10-14 cs.CV cs.AI cs.LG cs.RO 82%

Vision-Language Cross-Attention for Real-Time Autonomous Driving

Santosh Patapati, Trisanth Srinivasan, Murari Ambati

机构 * Cyrion Labs（Cyrion实验室）

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

Comments 5 pages

2506.13265 2025-09-04 cs.CV cs.AI cs.LG cs.RO 82%

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

Rohit Mohan, Julia Hindel, Florian Drews, Claudius Gläser, Daniele Cattaneo, Abhinav Valada

机构 * Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系）； Bosch Research, Robert Bosch GmbH（博世研究）

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

2508.11868 2025-08-19 cs.RO cs.AI cs.CV 82%

Data Shift of Object Detection in Autonomous Driving

Lida Xu

机构 * Department of Computer Science and Engineering（计算机科学与工程系）

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

2507.20217 2025-07-30 cs.RO cs.AI cs.CV 82%

Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots

Wei Cui, Haoyu Wang, Wenkang Qin, Yijie Guo, Gang Han, Wen Zhao, Jiahang Cao, Zhang Zhang, Jiaru Zhong, Jingkai Sun, Pihai Sun, Shuai Shi, Botuo Jiang, Jiahao Ma, Jiaxu Wang, Hao Cheng, Zhichao Liu, Yang Wang, Zheng Zhu, Guan Huang, Jian Tang, Qiang Zhang

机构 * X-Humanoid ； GigaAI Project（GigaAI项目）

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

Comments Tech Report

1. 感知 6049 篇

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection

Recognizing and Tracking High-Level, Human-Meaningful Navigation Features of Occupancy Grid Maps

MultiNet: Multi-Modal Multi-Task Learning for Autonomous Driving

Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks

Mapless Online Detection of Dynamic Objects in 3D Lidar

Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learning

LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR

Fusing Bird View LIDAR Point Cloud and Front View Camera Image for Deep Object Detection

Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Driving

Free Space Estimation using Occupancy Grids and Dynamic Object Detection

Multi-View 3D Object Detection Network for Autonomous Driving

SoildNet: Soiling Degradation Detection in Autonomous Driving

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object Tracking

RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception

UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception

WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems

Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection

Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving

Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving

An Efficient LiDAR-Camera Fusion Network for Multi-Class 3D Dynamic Object Detection and Trajectory Prediction

Failure Analysis of Safety Controllers in Autonomous Vehicles Under Object-Based LiDAR Attacks

Fractured Glass, Failing Cameras: Simulating Physics-Based Adversarial Samples for Autonomous Driving Systems

Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?

On the Robustness Evaluation of 3D Obstacle Detection Against Specifications in Autonomous Driving

Vision-Language Cross-Attention for Real-Time Autonomous Driving

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

Data Shift of Object Detection in Autonomous Driving

Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots