cs.RO（2026-02-13）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#题目一句话要点标签🔗⭐
1 CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation CLOT：基于闭环全局运动跟踪实现全身人形机器人遥操作 humanoid sim-to-real teleoperation
2 FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation FlowHOI：基于流模型生成语义驱动的手-物交互，用于灵巧机器人操作 manipulation dexterous manipulation flow matching
3 PMG: Parameterized Motion Generator for Human-like Locomotion Control 提出参数化运动生成器PMG，实现类人运动控制与高效的Sim-to-Real迁移 humanoid humanoid control humanoid locomotion
4 CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning CRAFT：通过力感知的课程微调，使VLA模型适应接触式操作 manipulation teleoperation vision-language-action
5 Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models 提出基于强化学习的Sim-Real协同训练框架RL-Co，提升VLA模型在真实机器人操作任务中的性能。 manipulation reinforcement learning vision-language-action
6 Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution 小米提出Xiaomi-Robotics-0，一种用于实时执行的开源视觉-语言-动作模型 manipulation bi-manual bimanual manipulation
7 TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions 提出TRANS框架，实现四足机器人在复杂地形和社交环境下的敏捷导航 quadruped locomotion sim-to-real
8 SENSE-STEP: Learning Sim-to-Real Locomotion for a Sensory-Enabled Soft Quadruped Robot SENSE-STEP：面向软体四足机器人，学习基于触觉感知的Sim-to-Real运动控制 quadruped locomotion sim-to-real
9 ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training ALOE：用于视觉-语言-动作模型后训练的动作级离策略评估框架 manipulation bi-manual reinforcement learning
10 UniManip: General-Purpose Zero-Shot Robotic Manipulation with Agentic Operational Graph 提出UniManip以解决通用零-shot机器人操作问题 manipulation mobile manipulation vision-language-action ✅
11 Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control 提出可操纵的视觉-语言-动作策略，用于具身推理和分层控制。 manipulation vision-language-action VLA
12 Learning Native Continuation for Action Chunking Flow Policies Legato：面向动作分块流程策略的连续性学习方法，提升VLA模型平滑性和效率 manipulation vision-language-action VLA
13 Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Models Real2Gen：利用生成式模型，从单个人类演示中学习机器人操作策略 manipulation teleoperation imitation learning
14 Agentic AI for Robot Control: Flexible but still Fragile 提出基于代理智能的机器人控制系统以应对不确定性问题 manipulation mobile manipulation affordance
15 Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos 提出PSI框架，通过模拟过滤的人类视频学习模块化操作策略，提升机器人操作技能。 manipulation policy learning
16 Real-to-Sim for Highly Cluttered Environments via Physics-Consistent Inter-Object Reasoning 提出物理约束的Real-to-Sim流程，用于重建高杂乱环境下的物理一致性场景 manipulation penetration

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
17 AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge AsyncVLA：一种异步VLA框架，用于边缘端快速鲁棒导航 VLA foundation model
18 PISHYAR: A Socially Intelligent Smart Cane for Indoor Social Navigation and Multimodal Human-Robot Interaction for Visually Impaired People PISHYAR：面向视障人士的社交智能手杖，实现室内社交导航与多模态人机交互 large language model multimodal
19 How Do We Research Human-Robot Interaction in the Age of Large Language Models? A Systematic Review 系统性回顾：大型语言模型时代下人机交互研究的现状与未来 large language model
20 INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval 提出INHerit-SG，通过RAG检索增强的增量式分层语义场景图，提升机器人导航中人机交互能力。 large language model foundation model ✅
21 Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories Safe-SDL：为AI驱动的自动驾驶实验室建立安全边界与控制机制 foundation model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
22 RynnBrain: Open Embodied Foundation Models 提出RynnBrain：一个用于具身智能的开源时空基础模型 egocentric spatiotemporal VLA

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
23 Coverage Path Planning for Autonomous Sailboats in Inhomogeneous and Time-Varying Oceans: A Spatiotemporal Optimization Approach 提出时空优化框架，解决自治帆船在非均匀时变海洋环境下的覆盖路径规划问题 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页