cs.RO（2025-12-10）

📊 共 26 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (18 🔗4) 支柱三：空间感知 (Perception & SLAM) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (18 篇)

#题目一句话要点标签🔗⭐
1 One-Shot Real-World Demonstration Synthesis for Scalable Bimanual Manipulation BiDemoSyn：基于单样本真实演示合成可扩展的双臂操作数据 manipulation bi-manual bimanual
2 ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat ReMoSPLAT：基于高斯溅射的移动机械臂反应式控制 manipulation mobile manipulation ReMoS
3 REASAN: Learning Reactive Safe Navigation for Legged Robots REASAN：面向复杂动态环境，学习腿式机器人反应式安全导航 legged robot locomotion reinforcement learning ✅
4 A Hierarchical, Model-Based System for High-Performance Humanoid Soccer 提出一种分层、基于模型的系统，用于高性能人形机器人足球比赛。 humanoid humanoid robot locomotion
5 Scene-agnostic Hierarchical Bimanual Task Planning via Visual Affordance Reasoning 提出基于视觉可供性的场景无关分层双臂任务规划框架 manipulation bi-manual bimanual
6 Push Smarter, Not Harder: Hierarchical RL-Diffusion Policy for Efficient Nonprehensile Manipulation 提出HeRD：一种用于高效非抓取操作的分层RL-扩散策略 manipulation reinforcement learning diffusion policy ✅
7 Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation 提出TacThru-UMI，结合新型触觉视觉传感器与Transformer扩散策略，提升机器人操作精度。 manipulation imitation learning diffusion policy
8 UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories 提出UrbanNav以解决复杂城市环境中的语言引导导航问题 walking navigation
9 Development of a Compliant Gripper for Safe Robot-Assisted Trouser Dressing-Undressing 开发用于安全机器人辅助穿脱裤子的柔顺夹持器 manipulation grasping grasp
10 H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos 提出H2R-Grounder，实现无需配对数据的物理可信人机交互视频转换。 manipulation human-object interaction ✅
11 Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge OpenPI Comet在BEHAVIOR挑战赛中获得亚军，通过系统性研究提升具身智能性能。 manipulation mobile manipulation
12 GLaD: Geometric Latent Distillation for Vision-Language-Action Models GLaD：几何潜在蒸馏增强视觉-语言-动作模型的空间推理能力 manipulation VGGT
13 ViTA-Seg: Vision Transformer for Amodal Segmentation in Robotics ViTA-Seg：用于机器人非模态分割的视觉Transformer，提升遮挡场景下的抓取规划。 manipulation grasp
14 Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models 综述：面向接触密集型机器人任务的安全学习方法，从经典方法到安全具身智能 manipulation reinforcement learning ✅
15 Fast Functionally Redundant Inverse Kinematics for Robotic Toolpath Optimisation in Manufacturing Tasks 提出快速功能冗余逆运动学算法，优化机器人制造任务中的工具路径 manipulation
16 HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models HiF-VLA：利用运动表征进行双向时序推理，提升视觉-语言-动作模型的长时序操作能力 manipulation
17 Py-DiSMech: A Scalable and Efficient Framework for Discrete Differential Geometry-Based Modeling and Control of Soft Robots Py-DiSMech：基于离散微分几何的软机器人建模与控制高效框架 sim-to-real
18 Bridging the Basilisk Astrodynamics Framework with ROS 2 for Modular Spacecraft Simulation and Hardware Integration 提出Basilisk与ROS 2的轻量级桥接方案，用于模块化航天器仿真与硬件集成 model predictive control

🔬 支柱三：空间感知 (Perception & SLAM) (7 篇)

#题目一句话要点标签🔗⭐
19 D$^2$GSLAM: 4D Dynamic Gaussian Splatting SLAM D$^2$GSLAM：基于高斯表示的动态场景4D SLAM系统，实现动态环境下的精确重建与鲁棒跟踪。 SLAM gaussian splatting scene reconstruction
20 YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videos YOPO-Nav：利用单次视频的3DGS图进行视觉导航 3D gaussian splatting 3DGS gaussian splatting
21 Inertial Magnetic SLAM Systems Using Low-Cost Sensors 提出基于低成本惯性磁传感器的惯性磁SLAM系统，提升弱光环境定位精度。 visual odometry SLAM localization
22 LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating 提出LISN-Bench与Social-Nav-Modulator，实现基于语言指令的社交导航。 scene understanding navigation ✅
23 Super4DR: 4D Radar-centric Self-supervised Odometry and Gaussian-based Map Optimization Super4DR：面向4D雷达的自监督里程计与高斯优化建图 SLAM point cloud
24 High-Resolution Water Sampling via a Solar-Powered Autonomous Surface Vehicle 提出一种太阳能自主水面船，实现高分辨率水样采集与水质监测 navigation
25 Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics 提出Aion，将时序流动动态嵌入分层4D场景图，用于动态环境自主导航。 navigation

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

#题目一句话要点标签🔗⭐
26 Generalizable Collaborative Search-and-Capture in Cluttered Environments via Path-Guided MAPPO and Directional Frontier Allocation 提出PGF-MAPPO，解决复杂环境下的协同搜索捕获问题，实现零样本泛化。 reinforcement learning reward shaping

⬅️ 返回 cs.RO 首页 · 🏠 返回主页