cs.RO（2025-11-03）

📊 共 25 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗2) 支柱三：空间感知 (Perception & SLAM) (7) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 MOBIUS: A Multi-Modal Bipedal Robot that can Walk, Crawl, Climb, and Roll MOBIUS：一种可步行、爬行、攀爬和滚动的多模态双足机器人 bipedal bipedal robot biped
2 Scaling Cross-Embodiment World Models for Dexterous Manipulation 提出基于粒子位移的跨形态世界模型，实现灵巧操作的泛化。 manipulation dexterous manipulation world model
3 Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping 提出基于流匹配的轻量级驱动空间学习方法，用于全身软体机器人抓取 grasping grasp flow matching
4 Embodiment Transfer Learning for Vision-Language-Action Models 提出ET-VLA框架，通过具身迁移学习提升VLA模型在多机器人协作中的性能 bi-manual bimanual cross-embodiment
5 Phy-Tac: Toward Human-Like Grasping via Physics-Conditioned Tactile Goals 提出基于物理约束触觉目标的力最优稳定抓取方法Phy-Tac manipulation grasping grasp
6 GenDexHand: Generative Simulation for Dexterous Hands GenDexHand：面向灵巧手的生成式仿真，解决数据稀缺问题 manipulation dexterous hand dexterous manipulation ✅
7 Learning from Watching: Scalable Extraction of Manipulation Trajectories from Human Videos 提出一种基于视频理解和点追踪的操纵轨迹提取方法，用于从人类视频中学习 manipulation teleoperation pose estimation
8 Stein-based Optimization of Sampling Distributions in Model Predictive Path Integral Control 提出基于Stein变分梯度下降的MPPI控制，优化采样分布以提升轨迹规划性能。 bipedal biped walking
9 MO-SeGMan: Rearrangement Planning Framework for Multi Objective Sequential and Guided Manipulation in Constrained Environments MO-SeGMan：面向约束环境的多目标序列引导操作重排规划框架 manipulation
10 AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models AERMANI-VLM：基于结构化提示和推理的视觉语言模型在无人机操作中的应用 manipulation
11 Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation 提出基于条件扩散模型的接触图传递方法，实现通用灵巧抓取生成。 grasp
12 TRACE: Textual Reasoning for Affordance Coordinate Extraction TRACE：利用文本推理提升视觉语言模型在机器人操作中的空间定位精度 manipulation affordance prediction ✅
13 CaRLi-V: Camera-RADAR-LiDAR Point-Wise 3D Velocity Estimation CaRLi-V：提出相机-雷达-激光雷达融合的点云级三维速度估计方法 manipulation optical flow
14 RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models RobustVLA：面向视觉-语言-动作模型的鲁棒性强化后训练 manipulation reinforcement learning
15 Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects Kinematify：开放词汇高自由度铰接物体自动合成框架 motion planning policy learning
16 Design and development of an electronics-free earthworm robot 提出一种无需电子元件的蠕虫机器人，适用于受限和非结构化环境。 locomotion
17 Design and Fabrication of Origami-Inspired Knitted Fabrics for Soft Robotics 提出一种基于针织面料的折纸结构软体机器人设计与制造方法 locomotion

🔬 支柱三：空间感知 (Perception & SLAM) (7 篇)

#题目一句话要点标签🔗⭐
18 LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping 提出LiDAR-VGGT，通过跨模态融合实现全局一致和度量尺度稠密地图重建 visual odometry lidar-inertial scene understanding
19 TurboMap: GPU-Accelerated Local Mapping for Visual SLAM TurboMap：面向视觉SLAM的GPU加速局部地图构建模块 visual SLAM SLAM
20 Floor Plan-Guided Visual Navigation Incorporating Depth and Directional Cues 提出GlocDiff，融合楼层平面图与深度信息的视觉导航方法 VO pose estimation localization
21 CM-LIUW-Odometry: Robust and High-Precision LiDAR-Inertial-UWB-Wheel Odometry for Extreme Degradation Coal Mine Tunnels CM-LIUW-Odometry：面向极端退化煤矿巷道的鲁棒高精度激光-惯性-UWB-轮速里程计 SLAM lidar-inertial scene reconstruction
22 Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference 提出基于稀疏可行假设采样和可靠批处理多阶段推理的框架，解决机器人重定位问题。 SLAM occupancy grid traversability
23 Hybrid Neural Network-Based Indoor Localisation System for Mobile Robots Using CSI Data in a Robotics Simulator 提出一种基于混合神经网络的室内定位系统，利用CSI数据为移动机器人实现精准定位。 navigation
24 Lateral Velocity Model for Vehicle Parking Applications 提出基于实车数据的横向速度模型，提升自动泊车定位精度 localization

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
25 FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths FoldPath：通过调制隐式路径实现端到端面向对象的运动生成 motion generation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页