cs.RO（2026-02-18）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (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)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation HERO：结合视觉大模型与模拟训练，实现人型机器人开放词汇视觉操作控制 humanoid humanoid robot manipulation
2 EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data EgoScale：利用大规模第一人称视角人类数据扩展灵巧操作 manipulation dexterous manipulation egocentric
3 Dynamic Modeling and MPC for Locomotion of Tendon-Driven Soft Quadruped 提出基于Cosserat杆理论和MPC的肌腱驱动软体四足机器人运动控制方法 quadruped legged locomotion locomotion
4 One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation 提出一种参数化的规范表示，用于统一灵巧手操作并实现跨embodiment泛化。 manipulation dexterous hand dexterous manipulation
5 RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation RoboGene：通过多样性驱动的Agentic框架提升VLA预训练，用于真实世界任务生成 manipulation dual-arm physically plausible
6 Articulated 3D Scene Graphs for Open-World Mobile Manipulation MoMa-SG：为开放世界移动操作构建可交互物体的语义-运动3D场景图 quadruped manipulation mobile manipulation
7 VIGOR: Visual Goal-In-Context Inference for Unified Humanoid Fall Safety VIGOR：用于统一人形机器人跌倒安全的视觉上下文目标推理 quadruped humanoid fall recovery
8 Learning to unfold cloth: Scaling up world models to deformable object manipulation 提出基于DreamerV2改进的强化学习方法，解决复杂形变物体（如布料）的操控问题 manipulation reinforcement learning world model
9 Markerless 6D Pose Estimation and Position-Based Visual Servoing for Endoscopic Continuum Manipulators 提出基于视觉的无标记6D位姿估计与伺服控制，用于内窥镜连续体机械臂的精准操作。 sim-to-real 6D pose estimation geometric consistency
10 Dual-Quadruped Collaborative Transportation in Narrow Environments via Safe Reinforcement Learning 提出基于安全强化学习的双足机器人狭窄环境协同运输方法 quadruped reinforcement learning
11 Nonplanar Model Predictive Control for Autonomous Vehicles with Recursive Sparse Gaussian Process Dynamics 提出基于递归稀疏高斯过程动态的非平面模型预测控制，用于自主车辆在复杂地形导航。 MPC model predictive control
12 System Identification under Constraints and Disturbance: A Bayesian Estimation Approach 提出一种贝叶斯系统辨识框架，用于高精度估计机器人状态轨迹和物理参数。 locomotion model predictive control Unitree
13 SIT-LMPC: Safe Information-Theoretic Learning Model Predictive Control for Iterative Tasks 提出SIT-LMPC算法，解决复杂不确定环境下迭代任务的鲁棒安全控制问题 model predictive control

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Reactive Motion Generation With Particle-Based Perception in Dynamic Environments 提出基于粒子动态感知的反应式运动生成方法，解决动态环境中机器人操作的避障问题 motion generation reactive motion

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 Markerless Robot Detection and 6D Pose Estimation for Multi-Agent SLAM 提出一种无需marker的多机器人SLAM方法，利用深度学习进行机器人检测和6D位姿估计。 6D pose estimation

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

#题目一句话要点标签🔗⭐
16 World Model Failure Classification and Anomaly Detection for Autonomous Inspection 提出一种基于世界模型的混合框架，用于自主巡检中的故障分类与异常检测。 world model

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

#题目一句话要点标签🔗⭐
17 Reactive Slip Control in Multifingered Grasping: Hybrid Tactile Sensing and Internal-Force Optimization 提出一种混合触觉传感与内力优化的多指抓取滑移反应控制方法 multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页