arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

视觉与机器人

自动驾驶

自动驾驶感知、规划、BEV、占用预测、激光雷达和仿真评测。

2026-03-16 至 2026-03-16 共收录 8 信号源:cs.RO, cs.CV, eess.IV, cs.AI

1. 规划控制 8 篇

2603.12421 2026-03-16 cs.CV 83%

A Neuro-Symbolic Framework Combining Inductive and Deductive Reasoning for Autonomous Driving Planning

一种结合归纳推理与演绎推理的神经符号框架用于自动驾驶规划

Hongyan Wei, Wael AbdAlmageed

机构 * Clemson University(克莱姆森大学)

专题命中 规划控制 :autonomous driving(title,abstract);trajectory planning(abstract);分类 cs.CV

AI总结 本文提出一种神经符号框架,结合归纳与演绎推理提升自动驾驶规划的透明性和安全性,在nuScenes基准中优于现有方法。

Comments Under review. 16 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12607 2026-03-16 cs.RO cs.AI 81%

CarPLAN: Context-Adaptive and Robust Planning with Dynamic Scene Awareness for Autonomous Driving

CarPLAN: 基于动态场景感知的上下文自适应与鲁棒规划

Junyong Yun, Jungho Kim, ByungHyun Lee, Dongyoung Lee, Sehwan Choi, Seunghyeop Nam, Kichun Jo, Jun Won Choi

机构 * Department of Artificial Intelligence, Hanyang University(翰林大学人工智能系) Interdisciplinary Program in Artificial Intelligence, Seoul National University(首尔国立大学人工智能跨学科项目) Department of Electrical and Computer Engineering, Seoul National University(首尔国立大学电子与计算机工程系) Department of Automotive Engineering, Hanyang University(翰林大学汽车工程系)

专题命中 规划控制 :autonomous driving(title,abstract);分类 cs.RO、cs.AI

AI总结 CarPLAN通过位移感知预测编码和上下文自适应多专家解码器,提升自动驾驶在复杂场景中的鲁棒性和适应性规划能力。

Comments 10 pages, 6 figures. Under review at IEEE Transactions on Intelligent Transportation Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13136 2026-03-16 eess.SY cs.SY math.OC 78%

Unifying Decision Making and Trajectory Planning in Automated Driving through Time-Varying Potential Fields

通过时变势场统一决策与轨迹规划在自动驾驶中

David Costa, Francesco Cerrito, Massimo Canale, Carlo Novara

专题命中 规划控制 :trajectory planning(title,abstract)

AI总结 本文提出基于时变人工势场的统一决策与局部轨迹规划框架,通过建模动态障碍物的预测运动来实现安全轨迹生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11041 2026-03-16 cs.CV cs.RO 76%

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

DynVLA:为自动驾驶中的动作推理学习世界动态

Shuyao Shang, Bing Zhan, Yunfei Yan, Yuqi Wang, Yingyan Li, Yasong An, Xiaoman Wang, Jierui Liu, Lu Hou, Lue Fan, Zhaoxiang Zhang, Tieniu Tan

专题命中 规划控制 :autonomous driving(title);分类 cs.RO、cs.CV

AI总结 DynVLA提出一种新的Coot方法Dynamics CoT,通过预测紧凑世界动态来提升决策质量,实验表明其优于Textual CoT和Visual CoT。

Comments 18 pages, 10 figures. Project Page: https://yaoyao-jpg.github.io/dynvla

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.00547 2026-03-16 cs.CV cs.AI 62%

Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generation

Motion Dreamer:基于物理一致视频生成的边界条件运动推理

Tianshuo Xu, Zhifei Chen, Leyi Wu, Hao Lu, Yuying Chen, Lihui Jiang, Bingbing Liu, Yingcong Chen

专题命中 规划控制 :autonomous driving(abstract);分类 cs.CV、cs.AI

AI总结 本文提出Motion Dreamer框架,通过分离运动推理与视觉合成,解决视频生成中边界条件运动推理的问题,提升运动合理性与视觉真实性。

Comments The authors have decided to withdraw this article due to the following reasons identified after publication: Experimental Errors: Significant inaccuracies were discovered in the experimental results concerning segmentation and depth estimation. Authorship Disputes: In addition to the technical issues, there are unresolved disagreements regarding the author sequence and contributions

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12864 2026-03-16 cs.CV 57%

Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation

通过解耦控制合成驾驶世界以生成对抗性场景

Yifan Zhan, Zhengqing Chen, Qingjie Wang, Zhuo He, Muyao Niu, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Yinqiang Zheng

机构 * The University of Tokyo(东京大学) Horizon Robotics University of Glasgow(格拉斯哥大学)

专题命中 规划控制 :autonomous driving(abstract);分类 cs.CV

AI总结 本文提出CompoSIA,通过解耦交通因素实现对对抗性驾驶场景的精细控制,提升生成质量并减少误差。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12708 2026-03-16 cs.CV 57%

FSDAM: Few-Shot Driving Attention Modeling via Vision-Language Coupling

FSDAM:通过视觉-语言耦合实现少样本驾驶注意力建模

Kaiser Hamid, Can Cui, Khandakar Ashrafi Akbar, Ziran Wang, Nade Liang

机构 * Texas Tech University(德克萨斯理工大学) Purdue University(普渡大学) Towson University(托逊大学)

专题命中 规划控制 :autonomous driving(abstract);分类 cs.CV

AI总结 本文提出FSDAM框架,通过90个标注示例实现驾驶注意力预测与结构化解释生成,利用视觉-语言耦合减少标注需求,提升自动驾驶中的人机协作可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12771 2026-03-16 math.OC 50%

Improving critical buildings energy resilience via shared autonomous electric vehicles -- A sequential optimization framework

通过共享自动驾驶电动车提升关键建筑能源韧性——一种序列优化框架

Jinming Liu, Adam Abdin, Jakob Puchinger

专题命中 规划控制 :autonomous driving(abstract)

AI总结 本文提出一种序列优化框架,评估共享自动驾驶电动车通过V2B服务提升关键建筑能源韧性潜力,考虑乘客接驳、车辆调度及电池充放电,分析停电场景下的应急供电能力。

Journal ref Computers and Operations Research, 2024, 163

详情

展开后加载摘要…

URL PDF HTML 收藏