cs.RO（2026-02-27）

📊 共 20 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗4) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 Teleoperated Omni-directional Dual Arm Mobile Manipulation Robotic System with Shared Control for Retail Store 提出一种用于零售商店的遥操作全向双臂移动操作机器人系统，实现共享控制。 manipulation mobile manipulation dual-arm
2 OmniTrack: General Motion Tracking via Physics-Consistent Reference OmniTrack：通过物理一致性参考实现通用运动跟踪 humanoid humanoid robot teleoperation
3 FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation 提出FAVLA以解决接触丰富的机器人操作中的反应延迟问题 manipulation contact-aware vision-language-action
4 OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control OmniXtreme：突破高动态人形机器人控制的泛化性瓶颈 humanoid humanoid control sim-to-real
5 Humanoid Robots as First Assistants in Endoscopic Surgery 人形机器人首次辅助内窥镜手术，验证了形态可行性并识别了工程挑战。 humanoid humanoid robot teleoperation
6 StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation StemVLA：融合未来3D几何知识与4D历史表征的开放世界VLA模型 manipulation spatiotemporal vision-language-action
7 Interpretable Multimodal Gesture Recognition for Drone and Mobile Robot Teleoperation via Log-Likelihood Ratio Fusion 提出基于对数似然比融合的多模态手势识别框架，用于无人机和移动机器人遥操作。 teleoperation multimodal
8 VCA: Vision-Click-Action Framework for Precise Manipulation of Segmented Objects in Target Ambiguous Environments 提出VCA框架，通过视觉点击交互实现目标歧义环境下的精确物体操作 manipulation vision-language-action VLA ✅
9 Hybrid Offline-Online Reinforcement Learning for Sensorless, High-Precision Force Regulation in Surgical Robotic Grasping 提出混合离线-在线强化学习方法，用于手术机器人抓取中无传感、高精度力控制。 manipulation sim-to-real reinforcement learning
10 Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking 多物体抓取诊断视觉-语言动作策略中受限的泛化能力 manipulation VLA instruction following
11 Planning from Observation and Interaction 提出基于观察与交互的规划式逆强化学习，解决真实机器人环境下的世界建模问题 manipulation reinforcement learning behavior cloning ✅
12 ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation 提出ABPolicy，解决机器人操作中动作空间同步推理导致的平滑性与响应性问题。 manipulation flow matching ✅
13 Learning Robust Control Policies for Inverted Pose on Miniature Blimp Robots 提出一种鲁棒控制策略学习框架，用于微型飞艇机器人在倒立姿态下的稳定控制。 sim-to-real domain randomization policy learning
14 Curriculum Reinforcement Learning for Quadrotor Racing with Random Obstacles 提出基于课程强化学习的四旋翼无人机随机障碍竞速方法 domain randomization reinforcement learning ✅
15 Geometry-based pneumatic actuators for soft robotics 提出基于几何约束的气动软体驱动器，实现可预测形变和多状态控制 bipedal biped locomotion
16 Tilt-X: Enabling Compliant Aerial Manipulation through a Tiltable-Extensible Continuum Manipulator 提出Tilt-X：一种可倾斜伸缩的连续体机械臂，用于无人机柔顺空中操作 manipulation
17 SpikingTac: A Miniaturized Neuromorphic Visuotactile Sensor for High-Precision Dynamic Tactile Imprint Tracking SpikingTac：一种用于高精度动态触觉印记追踪的小型化神经形态视觉触觉传感器 manipulation

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

#题目一句话要点标签🔗⭐
18 Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos 提出STE-VLN，利用多模态事件知识增强视觉-语言导航中的长程推理能力。 egocentric spatiotemporal VLN

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
19 SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems SafeGen-LLM：提升机器人任务规划中安全泛化能力的大语言模型 reinforcement learning curriculum learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
20 KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning 提出KEEP，一种面向具身规划的高效KV缓存中心化内存管理系统 large language model ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页