机器人 / 具身智能

Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks

Yinda Zhang, Shuran Song, Ersin Yumer, Manolis Savva, Joon-Young Lee, Hailin Jin, Thomas Funkhouser

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

Comments Updates camera ready version. Accepted by CVPR 2017

Geometry of 3D Environments and Sum of Squares Polynomials

Amir Ali Ahmadi, Georgina Hall, Ameesh Makadia, Vikas Sindhwani

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

CoSTAR: Instructing Collaborative Robots with Behavior Trees and Vision

Chris Paxton, Andrew Hundt, Felix Jonathan, Kelleher Guerin, Gregory D. Hager

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

STAM: A Framework for Spatio-Temporal Affordance Maps

Francesco Riccio, Roberto Capobianco, Marc Hanheide, Daniele Nardi

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

Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories

Przemysław Andrzej Wałęga, Carl Schultz, Mehul Bhatt

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

Comments 22 pages, 6 figures, Under consideration for publication in TPLP

Structured Factored Inference: A Framework for Automated Reasoning in Probabilistic Programming Languages

Avi Pfeffer, Brian Ruttenberg, William Kretschmer

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

ASPMT(QS): Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories

Przemysław Andrzej Wałęga, Mehul Bhatt, Carl Schultz

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

Comments pages 13. accepted for publication at: LPNMR 2015 - Logic Programming and Nonmonotonic Reasoning, 13th International Conference, LPNMR 2015, LNAI Vol. 9345., Lexington, September 27-30, 2015. Proceedings., (editors: Francesco Calimeri, Giovambattista Ianni, Miroslaw Truszczynski)

On the Internal Topological Structure of Plane Regions

Sanjiang Li

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

Comments A short version appeared in KR-10. Several results have been rephrased and omitted proofs are given here. (Sanjiang Li. A Layered Graph Representation for Complex Regions, in Proceedings of the 12th International Conference on the Principles of Knowledge Representation and Reasoning (KR-10), pages 581-583, Toronto, Canada, May 9-13, 2010)

Relations World: A Possibilistic Graphical Model

Christopher J. C. Burges, Erin Renshaw, Andrzej Pastusiak

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

Comments 10 pages

A Representation of Uncertainty to Aid Insight into Decision Models

Holly B. Jimison

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

Comments Appears in Proceedings of the Fourth Conference on Uncertainty in Artificial Intelligence (UAI1988)

The Bounded Bayesian

Kathryn Blackmond Laskey

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

Comments Appears in Proceedings of the Eighth Conference on Uncertainty in Artificial Intelligence (UAI1992)

An Approach For Robots To Deal With Objects

Sidiq S. Hidayat, Bong Keung Kim, Kohtaro Ohba

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

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity

Juergen Schmidhuber

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

Comments 15 pages, 3 highly compressible low-complexity drawings. Joint Invited Lecture for Algorithmic Learning Theory (ALT 2007) and Discovery Science (DS 2007), Sendai, Japan, 2007

From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs

从USD场景到知识图谱：基于LLM的零样本本体接地

Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth, Sonja Schimmler

机构 * Technical University of Berlin（柏林工业大学） ； Fraunhofer FOKUS（弗劳恩霍夫开放通信系统研究所） 纠错

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

AI总结 研究利用大语言模型（LLM）零样本地将3D场景对象自动映射到本体类别，无需训练，在厨房场景中达到90-96%准确率，并揭示语义线索是关键。

Comments Accepted to the IEEE ICRA 2026 International Joint Workshop on Ontologies, Semantic Maps and Autonomous Robotics Standardization (J-WOSMARS 2026), Vienna, 2026

BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

BulletGen: 通过子弹时间生成提升4D重建

Denis Rozumny, Jonathon Luiten, Numair Khan, Johannes Schönberger, Peter Kontschieder

机构 * Meta Reality Labs（Meta 现实实验室） 纠错

专题命中 具身推理 ：分类 cs.AI、cs.CV、cs.LG；world model(comments)

AI总结 BulletGen利用生成模型在Gaussian动态场景表示中校正错误并补全缺失信息，通过对扩散视频生成模型输出与4D重建在单个冻结子弹时间步骤的对齐，实现新颖视角合成和2D/3D跟踪任务的最先进结果。

Comments Accepted at CVPR 2026 Workshop "4D World Models: Bridging Generation and Reconstruction"

Enhancing Long Video Generation Consistency without Tuning

Xingyao Li, Fengzhuo Zhang, Jiachun Pan, Yunlong Hou, Vincent Y. F. Tan, Zhuoran Yang

机构 * National University of Singapore（新加坡国立大学） ； Yale University（耶鲁大学） 纠错

专题命中 具身推理 ：分类 cs.AI、cs.CV、cs.LG；world model(comments)

Comments ICML 2025 Workshop on Building Physically Plausible World Models (Best Paper), 32 pages, 17 figures

Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot

Pradip Pramanick, Chayan Sarkar, Snehasis Banerjee, Brojeshwar Bhowmick

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

Comments Accepted in Elsevier Journal of Robotics and Autonomous Systems (RAS)

Can I Pour into It? Robot Imagining Open Containability Affordance of Previously Unseen Objects via Physical Simulations

Hongtao Wu, Gregory S. Chirikjian

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

Comments IEEE Robotics and Automation Letters. Video demos are available on https://chirikjianlab.github.io/realcontainerimagination/

Action-Based Representation Learning for Autonomous Driving

Yi Xiao, Felipe Codevilla, Christopher Pal, Antonio M. Lopez

专题命中 具身推理 ：分类 cs.RO、cs.CV、cs.LG；robot learning(comments)

Comments This paper has been accepted to the Conference on Robot Learning (CoRL 2020)

COSMO: Contextualized Scene Modeling with Boltzmann Machines

Ilker Bozcan, Sinan Kalkan

专题命中 具身推理 ：分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments 40 pages, 15 figures, 9 tables, accepted to the Robotics and Autonomous Systems (RAS) special issue on Semantic Policy and Action Representations for Autonomous Robots (SPAR)

Grounded Lexicon Acquisition - Case Studies in Spatial Language

Michael Spranger

专题命中 具身推理 ：world model(abstract)；robotics(comments)

Comments Development and Learning and Epigenetic Robotics (ICDL-Epirob), 2013 Joint IEEE International Conferences on, pages 1-6. IEEE

Towards Learning Object Affordance Priors from Technical Texts

Nicholas H. Kirk

专题命中 具身推理 ：分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments "Active Learning in Robotics" Workshop, IEEE-RAS International Conference on Humanoid Robots [accepted]

REACT3D: Recovering Articulations for Interactive Physical 3D Scenes

REACT3D: 交互式物理3D场景中关节的恢复

Zhao Huang, Boyang Sun, Alexandros Delitzas, Jiaqi Chen, Marc Pollefeys

机构 * ETH Zurich（苏黎世联邦理工学院） ； Max Planck Institute for Informatics（马克斯·普朗克信息学研究所） ； Microsoft Spatial AI Lab（微软空间人工智能实验室） 纠错

专题命中 具身推理 ：robotics(comments,journal_ref)；分类 cs.RO、cs.CV

AI总结 REACT3D通过零样本框架实现静态3D场景到可交互模拟的转换，解决了标注过程繁琐的问题，提升了多任务应用的兼容性与效率。

Comments Accepted at IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 5, pp. 5954-5961, May 2026

Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images

Nikhil Gosala, Abhinav Valada

专题命中 具身推理 ：robotics(comments,journal_ref)；分类 cs.RO、cs.CV

Comments 17 pages, 13 figures, Accepted for publication in the IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, Volume 7, Issue 2, April 2022, pp. 1968-1975

Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes

Nicolas Marchal, Charlotte Moraldo, Roland Siegwart, Hermann Blum, Cesar Cadena, Abel Gawel

专题命中 具身推理 ：robotics(comments,journal_ref)；分类 cs.RO、cs.CV

Comments Preprint version after acceptance of publication in the IEEE robotics and automation letters

Journal ref IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 1032-1038, April 2020

The Modeler-Schema Theory of Consciousness: Diffuse Awareness, Focal Experience, and a Saccadic Consistency Experiment

意识的模型者图式理论，附可证伪实验

Frank Heile

专题命中 具身推理 ：world model(abstract)

AI总结 提出意识源于单一控制代理——模型者图式，它监控模型者构建内部世界模型的过程，通过将模型者输出转化为感受质产生体验，并用于模型优化；通过扫视变化检测实验区分两种自下而上注意请求，为意识难题提供可检验方案。

Comments 35 pages, 4 figures

Ten Years of Deep Learning for Wireless Communications: From Learned Blocks to Deployable Wireless Intelligence

十年深度学习在无线通信中的应用：从学习模块到可部署的无线智能

Hao Ye, Geoffrey Ye Li, Biing-Hwang Juang

专题命中 具身推理 ：world model(abstract)

AI总结 本文梳理了十年间深度学习在无线通信领域从替代孤立模块到开发无线智能的三次转变，指出未来无线AI发展需结合物理基础、智能体能力与标准化机制。

Critical Inertia Estimation for the Three U.S. Interconnections

美国三大互联电网的关键惯量估计

Jiaojiao Dong, Sneha Fariha, Rocio Uria Martinez, Wen Wang, Yilu Liu

专题命中 具身推理 ：world model(abstract)

AI总结 该研究针对美国三大互联电网，通过全尺寸PSS/E和PowerWorld模型仿真，得出不同电网的关键惯量对应的IBRs渗透率，指出需用全动态仿真指导高可再生能源下的输电规划。

Who's That Player?: Externalizing Query Interpretation in Spoken XR Sports Interaction

那个球员是谁？：在沉浸式体育交互中外部化查询解释

Chunggi Lee, Tica Lin, Yalong Yang, Hanspeter Pfister

专题命中 具身推理 ：navigation(abstract)

AI总结 本研究针对XR体育观赛中语音查询歧义导致的误读问题，构建外部化查询解释的设计空间并开发XR足球系统，用户研究显示外部化可提升可检查性但存在可见性-行动差距。

Entanglement Entropy and Complexity of Multicomponent Universe from Holography

从全息学角度研究多组分宇宙的纠缠度量

Ritam Mahanta, Gopinath Guin, Souvik Paul, Sunandan Gangopadhyay

专题命中 具身推理 ：world model(abstract)

AI总结 本文提出了一种研究多组分宇宙全息信息理论量的方法，展示了双组分物质源的宇宙模型及其在不同时间尺度下的行为特征。

Comments 38 Pages, 1 Figure, Accepted for publication in Progress of Theoretical and Experimental Physics

Journal ref Prog. Theor. Exp. Phys. 2026 073B11