cs.RO（2026-04-16）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion 基于模型的强化学习利用被动身体动力学实现高性能双足机器人运动 humanoid biped locomotion
2 Switch: Learning Agile Skills Switching for Humanoid Robots Switch：面向人形机器人的敏捷技能切换学习方法 humanoid humanoid robot whole-body control
3 World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems 提出World-Value-Action模型，用于提升视觉-语言-动作系统中长时程规划能力 trajectory optimization world model world models
4 DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation DockAnywhere：通过新颖的演示生成方法，实现移动操作中数据高效的视觉运动策略学习 manipulation mobile manipulation policy learning
5 A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics 提出一种层级时空动作Tokenizer，用于机器人上下文模仿学习，实现SOTA性能。 manipulation imitation learning spatiotemporal
6 Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios 针对视障人士，提出动量约束混合启发式轨迹优化框架，提升安全性与舒适性。 trajectory optimization reinforcement learning deep reinforcement learning
7 DEX-Mouse: A Low-cost Portable and Universal Interface with Force Feedback for Data Collection of Dexterous Robotic Hands DEX-Mouse：一种低成本、便携式、通用且具力反馈的灵巧手遥操作数据采集接口 manipulation dexterous hand dexterous manipulation
8 HRDexDB: A Large-Scale Dataset of Dexterous Human and Robotic Hand Grasps HRDexDB：用于灵巧操作的大规模人手与机械手抓取数据集 manipulation dexterous manipulation policy learning
9 Abstract Sim2Real through Approximate Information States 提出基于近似信息状态的抽象Sim2Real方法，解决抽象模拟器向真实环境迁移问题 sim2real reinforcement learning
10 Differentiable Object Pose Connectivity Metrics for Regrasp Sequence Optimization 提出基于可微姿态连通性度量的重抓取序列优化方法，提升机器人操作的鲁棒性。 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
11 CAVERS: Multimodal SLAM Data from a Natural Karstic Cave with Ground Truth Motion Capture CAVERS：提供含地面真值运动捕捉的天然喀斯特洞穴多模态SLAM数据集 3D reconstruction multimodal ✅
12 CT-VIR: Continuous-Time Visual-Inertial-Ranging Fusion for Indoor Localization with Sparse Anchors 提出CT-VIR，利用连续时间视觉惯性测距融合实现稀疏锚点的室内定位 VIO

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
13 Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees 提出基于视觉的置信安全人机协作框架，保障不确定性下的安全 human motion human motion prediction motion prediction

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

#题目一句话要点标签🔗⭐
14 Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye 提出CAL2M以解决公里级SLAM中的标定问题 feature matching foundation model ✅

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

#题目一句话要点标签🔗⭐
15 POMDP-based Object Search with Growing State Space and Hybrid Action Domain 提出GNPF-kCT算法，解决复杂环境下移动机器人基于POMDP的目标搜索问题 world model world models large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页