arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

机器人 / 具身智能

机器人、具身智能、机器人学习、操作、导航和具身世界模型。

共收录 3091 信号源:cs.RO, cs.AI, cs.CV, cs.LG

1. 具身推理 3091 篇

0707.2199 2009-12-01 astro-ph 78%

Observational constraints on the braneworld model with brane-bulk energy exchange

M. Sadegh Movahed, Ahmad Sheykhi

专题命中 具身推理 :world model(title,abstract)

Comments 17 pages and 18 figures, V2: Added comments, references, explained some topics related to the matter power spectrum as a robust constraint, accepted for publication in Mon. Not. R. Astron. Soc

Journal ref Mon. Not. R. Astron. Soc. 388, 197- 210 (2008)

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-ph/0603217 2009-12-01 hep-ph 78%

Fermion Confinement in Brane World Models with SO(10) Unification

David Curtin

专题命中 具身推理 :world model(title,abstract)

Comments Honours thesis 2005, School of Physics, University of Melbourne, Supervised by Raymond R. Volkas

详情

展开后加载摘要…

URL PDF HTML 收藏
gr-qc/0604071 2009-12-01 gr-qc astro-ph hep-th 78%

Weaker Gravity at Submillimetre Scales in Braneworld Models

Claudia de Rham, Tetsuya Shiromizu, Andrew J. Tolley

专题命中 具身推理 :world model(title,abstract)

Comments References added, typos corrected

详情

展开后加载摘要…

URL PDF HTML 收藏
astro-ph/0502032 2009-12-01 astro-ph gr-qc hep-ph hep-th 78%

Cosmological Surprises from Braneworld models of Dark Energy

Varun Sahni

专题命中 具身推理 :world model(title,abstract)

Comments latex 21 pages, 11 figures; Invited talk at the 14th international workshop on General relativity and Gravitation, Yukawa Institute for Theoretical Physics, Nov 29-Dec 3, 2004, Kyoto, Japan. An important comment added in section 6; additional references

Journal ref Proceedings of the 14th Workshop on General relativity and Gravitation (JGRG14), Kyoto University, Japan 29 November - 3 December, 2004. Edited by W. Hikida, M. Sasaki, T. Tanaka and T. Nakamura; p 95 - 115.

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0504205 2009-12-01 hep-th 78%

The Gospel according to DeWitt revisited: quantum effective action in braneworld models

A. O. Barvinsky

专题命中 具身推理 :world model(title,abstract)

Comments LaTeX, 14 pages, talk given at Bryce DeWitt memorial session of the International Conference on Theoretical Physics, 70 years Jubilee of the I.E.Tamm Theory Department of the Lebedev Physics Institute, Moscow, April 11-16, 2005

详情

展开后加载摘要…

URL PDF HTML 收藏
gr-qc/0305031 2009-11-30 gr-qc 78%

Weak gravity in DGP braneworld model

Takahiro Tanaka

专题命中 具身推理 :world model(title,abstract)

Comments 7 pages, 1 figure, references added

Journal ref Phys.Rev. D69 (2004) 024001

详情

展开后加载摘要…

URL PDF HTML 收藏
astro-ph/0305123 2009-11-30 astro-ph gr-qc hep-ph hep-th 78%

Second-order Perturbations of the Friedmann World Model

H. Noh, J. Hwang

专题命中 具身推理 :world model(title,abstract)

Comments 61 pages; published version in Phys. Rev. D

Journal ref Phys. Rev. D 69 (2004) 104011

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0210086 2009-11-30 hep-th astro-ph 78%

Varying Fundamental Constants from a String-inspired Brane World Model

Cristiano Germani, Carlos F. Sopuerta

专题命中 具身推理 :world model(title,abstract)

Comments 6 pages, 1 fig., LaTeX (Kluwer style). Contribution to JENAM 2002 (VFC workshop) Corrections added to match final version

Journal ref Astrophys.Space Sci. 283 (2003) 487-492

详情

展开后加载摘要…

URL PDF HTML 收藏
gr-qc/0204040 2009-11-30 gr-qc astro-ph hep-ph hep-th 78%

New Cosmological Singularities in Braneworld Models

Yuri Shtanov, Varun Sahni

专题命中 具身推理 :world model(title,abstract)

Comments 11 pages, 3 figures. Slight change in title to match version accepted for publication in Class. Quant. Grav. (Lett.)

Journal ref Class.Quant.Grav.19:L101-L107,2002

详情

展开后加载摘要…

URL PDF HTML 收藏
astro-ph/0202346 2009-11-30 astro-ph gr-qc hep-ph hep-th 78%

Braneworld models of dark energy

Varun Sahni, Yuri Shtanov

专题命中 具身推理 :world model(title,abstract)

Comments 17 pages, latex, 8 figures. Minor changes to match version published in JCAP

Journal ref JCAP 0311 (2003) 014

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0107227 2009-11-30 hep-th gr-qc hep-ph 78%

Comments on conformal stability of brane-world models

M. Bouhmadi-Lopez, A. Zhuk

专题命中 具身推理 :world model(title,abstract)

Comments 13 pages, LateX2e, two references added

Journal ref Phys.Rev. D65 (2002) 044009

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-ph/0111061 2009-11-30 hep-ph astro-ph gr-qc hep-th 78%

Non-topological solitons in brane world models

Dejan Stojkovic

专题命中 具身推理 :world model(title,abstract)

Comments version accepted for publication in Physical Review D

Journal ref Phys.Rev. D67 (2003) 045012

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0006184 2009-11-30 hep-th hep-ph 78%

A Brane World Model with Intersecting Branes

Matej Pavsic

专题命中 具身推理 :world model(title,abstract)

Comments 14 pages

Journal ref Phys.Lett. A283 (2001) 8

详情

展开后加载摘要…

URL PDF HTML 收藏
astro-ph/9909150 2009-11-30 astro-ph gr-qc 78%

Conserved quantities in the perturbed Friedmann world model

J. Hwang

专题命中 具身推理 :world model(title,abstract)

Comments 4 pages, no figure, Proceedings of The 2nd Seoul Workshop on Gravitation and Cosmology

Journal ref J.KoreanPhys.Soc.35:S633-S637,1999; J.KoreanPhys.Soc.35:S633-637,1999

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0302221 2009-11-30 hep-th 78%

Gauge Threshold Corrections in Intersecting Brane World Models

D. Lust, S. Stieberger

专题命中 具身推理 :world model(title,abstract)

Comments 51 pages, harvmac

Journal ref Fortsch.Phys.55:427-465,2007

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0111291 2009-11-30 hep-th 78%

Perfect fluid brane-world model

M. Bouhmadi-Lopez, P. F. Gonzalez-Diaz, A. Zhuk

专题命中 具身推理 :world model(title,abstract)

Comments 14 pages, LateX2e, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
hep-th/0105240 2009-11-30 hep-th 78%

Dynamical Instabilities of Brane World Models

J. Diemand, Ch. Mathys, D. Wyler

专题命中 具身推理 :world model(title,abstract)

Comments 11 pages, no figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2107.03038 2021-07-08 cs.RO cs.CV 77%

Maintaining a Reliable World Model using Action-aware Perceptual Anchoring

Ying Siu Liang, Dongkyu Choi, Kenneth Kwok

专题命中 具身推理 :world model(title);分类 cs.RO、cs.CV;robotics(journal_ref)

Comments 7 pages, 3 figures

Journal ref 2021 International Conference on Robotics and Automation (ICRA 2021)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10915 2026-08-13 cs.AI 版本更新 77%

ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

具身融合智能体:以人为中心的智能体人工智能新范式

Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Yao, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, Bang Liu

机构 * Université de Montréal(蒙特利尔大学) Mila – Quebec Artificial Intelligence Institute(米拉-魁北克人工智能研究所) Institute of Advanced Intelligence and Computing (IAIC), A*STAR(新加坡科技研究局高级智能与计算研究所) Nanjing Medical University(南京医科大学) Nanjing University(南京大学) Renmin University of China(中国人民大学) University of Cambridge(剑桥大学) University of Oxford(牛津大学) Tsinghua University(清华大学) National University of Singapore(新加坡国立大学) The Hong Kong University of Science and Technology(香港科技大学) The Hong Kong Polytechnic University(香港理工大学) Southern University of Science and Technology(南方科技大学) Southeast University(东南大学) University of Glasgow(格拉斯哥大学) Nanyang Technological University(南洋理工大学)

专题命中 具身推理 :world model(abstract,abstract_cn);embodied agent(abstract);分类 cs.AI

AI总结 该研究提出以人为中心的 Combodied Agents 新范式,整合多类智能体能力形成闭环,聚焦人类状态轨迹建模,推动智能体 AI 从任务完成转向人类持续福祉。

Comments 38 pages, 6 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19990 2026-08-11 cs.AI 版本更新 77%

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

LEGO-Puzzles:多模态大语言模型(MLLMs)在多步骤空间推理上的表现如何?

Kexian Tang, Junyao Gao, Yanhong Zeng, Haodong Duan, Yanan Sun, Zhening Xing, Wenran Liu, Kai Chen, Kaifeng Lyu

机构 * Shanghai AI Laboratory(上海人工智能实验室) Tongji University(同济大学) Tsinghua University(清华大学)

专题命中 具身推理 :manipulation(abstract);navigation(abstract);robotic(abstract);分类 cs.AI

AI总结 该研究推出多步骤空间推理基准LEGO-Puzzles,评估29个顶尖MLLMs,发现其在基础空间推理、多步骤规划任务上远逊于人类,凸显其空间推理能力存在关键局限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.23312 2026-06-23 cs.RO 新提交 77%

From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models

从像素到概念:利用基础模型构建丰富的3D语义场景图森林

David Oberacker, Meike Deitersen, Niklas Spielbauer, Tristan Schnell, Georg Heppner, Arne Roennau

机构 * FZI Research Center for Information Technology(FZI信息技术研究中心) Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT)(卡尔斯鲁厄理工学院机器智能与机器人实验室)

专题命中 具身推理 :robotics(abstract);world model(abstract);robotic(abstract);分类 cs.RO

AI总结 提出利用基础模型构建具有开放语义关系的3D场景图森林,通过VLM和LLM推理抽象概念节点与关系,提升机器人场景理解与任务执行能力。

Comments To be published in the Proceedings of the IEEE/RSJ International Conference on Intelligent Robots & Systems (IEEE IROS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19253 2026-06-18 cs.CV cs.AI cs.LG cs.RO 新提交 77%

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

OneCanvas: 通过全景重投影实现3D场景理解

Bartłomiej Baranowski, Dave Zhenyu Chen, Matthias Nießner

机构 * Technical University of Munich(慕尼黑技术大学) Huawei(华为)

专题命中 具身推理 :robotics(abstract);embodied AI(abstract);分类 cs.RO、cs.AI、cs.CV

AI总结 提出OneCanvas方法,将多视图补丁特征聚合到全景画布上,利用深度和相机位姿进行重投影,无需复杂几何编码器或大量训练,在SQA3D等基准上达到最先进精度。

Comments Project page: https://baranowskibrt.github.io/onecanvas/

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14482 2026-06-12 cs.CV 版本更新 77%

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

V-JEPA 2.1: 解锁视频自监督学习中的密集特征

Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes

机构 * FAIR at Meta(Meta的FAIR) Universidad de Zaragoza(萨拉戈萨大学)

专题命中 具身推理 :navigation(abstract);world model(abstract);robotic(abstract);分类 cs.CV

AI总结 提出V-JEPA 2.1系列自监督模型,通过密集预测损失、深度自监督、多模态分词器和有效缩放,学习图像和视频的密集高质量视觉表示,在多个基准上取得最优性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05540 2026-04-22 cs.RO cs.AI cs.CV cs.LG cs.NE 77%

Constructing the Umwelt: Cognitive Planning through Belief-Intent Co-Evolution

构建环境:通过信念-意图共演的认知规划

Shiyao Sang

机构 * Shiyao Sang(桑世尧)

专题命中 具身推理 :world model(abstract,abstract_cn);分类 cs.RO、cs.AI、cs.CV

AI总结 本文提出基于信念-意图共演的认知规划方法,通过MBCWM和TIWM模型实现环境与现实的认知一致性,提升自动驾驶规划性能并展现类人认知行为。

Comments 12 pages, 8 figures. A paradigm shift from reconstructing the world to understanding it: planning through Belief-Intent Co-Evolution

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27967 2026-03-31 cs.CV 77%

Learning Multi-View Spatial Reasoning from Cross-View Relations

从跨视图关系学习多视图空间推理

Suchae Jeong, Jaehwi Song, Haeone Lee, Hanna Kim, Jian Kim, Dongjun Lee, Dong Kyu Shin, Changyeon Kim, Dongyoon Hahm, Woogyeol Jin, Juheon Choi, Kimin Lee

机构 * KAIST(韩国科学技术院) Config Hanyang University(汉阳大学) Yonsei University(延世大学) Seoul National University(首尔国立大学)

专题命中 具身推理 :embodied AI(abstract);manipulation(abstract);robotic(abstract);分类 cs.CV

AI总结 本文提出Cross-View Relations数据集,通过训练视觉语言模型提升多视图空间推理能力,在MindCube和RoboSpatial基准测试中取得显著提升,并在RoboCasa任务中提高机器人操作成功率。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13904 2026-03-26 cs.CV cs.AI cs.LG cs.RO 77%

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

单个token中的像素级场景理解:视觉状态需要什么在哪里的组成

Seokmin Lee, Yunghee Lee, Byeonghyun Pak, Byeongju Woo

机构 * Agency for Defense Development(国防发展机构)

专题命中 具身推理 :robot policy(abstract);robotic(abstract);分类 cs.RO、cs.AI、cs.CV

AI总结 本文提出CroBo框架,通过全局到局部重建目标,学习能捕捉场景元素语义身份和空间位置的视觉状态表示,以支持连续决策。

Comments Accepted to CVPR 2026 Workshop: Pixel-level Video Understanding in the Wild

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26255 2026-03-17 cs.AI cs.CV cs.LG cs.RO 77%

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning

ExoPredicator:为机器人规划学习动态世界的抽象模型

Yichao Liang, Dat Nguyen, Cambridge Yang, Tianyang Li, Joshua B. Tenenbaum, Carl Edward Rasmussen, Adrian Weller, Zenna Tavares, Tom Silver, Kevin Ellis

专题命中 具身推理 :robotics(abstract);world model(abstract);分类 cs.RO、cs.AI、cs.CV

AI总结 本文提出ExoPredicator框架,通过联合学习符号状态表示和因果过程,解决长周期具身规划中的外源性过程建模问题,实现对复杂任务的泛化能力。

Comments ICLR 2026. The last two authors contributed equally in co-advising

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17992 2025-12-23 cs.RO 77%

Unifying Deep Predicate Invention with Pre-trained Foundation Models

统一深度谓词发明与预训练基础模型

Qianwei Wang, Bowen Li, Zhanpeng Luo, Yifan Xu, Alexander Gray, Tom Silver, Sebastian Scherer, Katia Sycara, Yaqi Xie

机构 * Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所) Computer Science and Engineering Division, University of Michigan(密歇根大学计算机科学与工程系) Department of Computer Science, University of Pittsburgh(匹兹堡大学计算机科学系) Centaur AI Institute(Centaur人工智能研究所) Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系)

专题命中 具身推理 :robotics(abstract);world model(abstract);robotic(abstract);分类 cs.RO

AI总结 UniPred通过双层学习框架统一深度谓词发明与预训练基础模型,提升机器人任务的可扩展性和灵活性。

Comments 18 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11773 2025-11-12 cs.CV cs.HC 77%

AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments

Zikang Leng, Megha Thukral, Yaqi Liu, Hrudhai Rajasekhar, Shruthi K. Hiremath, Jiaman He, Thomas Plötz

专题命中 具身推理 :embodied AI(abstract);embodied agent(abstract);world model(abstract);分类 cs.CV

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12955 2025-07-17 cs.CV 77%

HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding

Jiahe Zhao, Ruibing Hou, Zejie Tian, Hong Chang, Shiguang Shan

机构 * Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS)(中国科学院人工智能安全重点实验室) Institute of Computing Technology, CAS(中国科学院计算技术研究所) University of CAS(中国科学院大学) Communication University of China(通信大学)

专题命中 具身推理 :embodied AI(abstract);embodied agent(abstract);world model(abstract);分类 cs.CV

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏