cs.RO（2025-11-12）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗3) 支柱三：空间感知 (Perception & SLAM) (5) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learning UMIGen：用于自中心点云生成和跨具身机器人模仿学习的统一框架 manipulation imitation learning visual SLAM
2 RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation 提出RGMP，融合几何先验与递归高斯过程，提升人形机器人操作的泛化性和数据效率。 humanoid humanoid robot manipulation
3 APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots APEX：利用动作先验实现腿式机器人稳健运动跟踪的高效探索 legged robot locomotion manipulation ✅
4 Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots 提出SCHUR框架与Humanoid-Union数据集，提升人形机器人高层控制的数据与模型可扩展性。 humanoid humanoid robot motion generation
5 IFG: Internet-Scale Guidance for Functional Grasping Generation IFG：利用互联网规模指导的功能性抓取生成 grasping grasp point cloud
6 ScaleADFG: Affordance-based Dexterous Functional Grasping via Scalable Dataset 提出ScaleADFG框架，解决机器人灵巧手对多尺度工具的功能性抓取问题。 manipulation grasping grasp ✅
7 MirrorLimb: Implementing hand pose acquisition and robot teleoperation based on RealMirror 提出基于RealMirror的MirrorLimb框架，实现低成本手部姿态获取和机器人遥操作 manipulation dexterous hand teleoperation
8 A Shared-Autonomy Construction Robotic System for Overhead Works 提出一种共享自主的建筑机器人系统，用于高空作业场景 bi-manual bimanual teleoperation
9 WMPO: World Model-based Policy Optimization for Vision-Language-Action Models 提出WMPO，用于视觉-语言-动作模型的基于世界模型的策略优化 manipulation reinforcement learning world model
10 SPIDER: Scalable Physics-Informed Dexterous Retargeting SPIDER：可扩展的基于物理信息的灵巧重定向框架，用于生成机器人控制策略。 humanoid dexterous hand reinforcement learning
11 SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation SpatialActor：探索解耦空间表征，提升机器人操作的鲁棒性 manipulation ✅
12 MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation MAP-VLA：利用记忆增强提示，提升VLA模型在机器人操作中的长时任务性能 manipulation
13 A Shared Control Framework for Mobile Robots with Planning-Level Intention Prediction 提出基于意图域预测的移动机器人共享控制框架，提升人机协作效率与安全性 teleoperation reinforcement learning deep reinforcement learning

🔬 支柱三：空间感知 (Perception & SLAM) (5 篇)

#题目一句话要点标签🔗⭐
14 SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields 提出基于稀疏运动场的直接视觉里程计SMF-VO，适用于资源受限设备。 visual odometry VO VIO
15 LODESTAR: Degeneracy-Aware LiDAR-Inertial Odometry with Adaptive Schmidt-Kalman Filter and Data Exploitation LODESTAR：基于自适应Schmidt-Kalman滤波和数据利用的抗退化LiDAR惯性里程计 lidar-inertial LIO
16 Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning 提出基于VLM推理的零样本物体目标导航方法，提升导航效率。 navigation
17 Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation 提出SCOPE框架以提升具身视觉导航的决策能力 navigation
18 XPRESS: X-Band Radar Place Recognition via Elliptical Scan Shaping XPRESS：基于椭圆扫描整形X波段雷达的地点识别方法，用于海事自主导航 navigation

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
19 CoRL-MPPI: Enhancing MPPI With Learnable Behaviours For Efficient And Provably-Safe Multi-Robot Collision Avoidance CoRL-MPPI：融合强化学习与MPPI，提升多机器人避障效率与安全性 reinforcement learning navigation
20 Baby Sophia: A Developmental Approach to Self-Exploration through Self-Touch and Hand Regard Baby Sophia：基于强化学习和自触摸、手部观察的机器人自主探索 reinforcement learning curriculum learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页