cs.RO（2025-10-27）

📊 共 23 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation ManiDP：面向姿态依赖的双臂操作，提出可操作性感知的扩散策略 manipulation bi-manual dual-arm
2 RoboOmni: Proactive Robot Manipulation in Omni-modal Context 提出RoboOmni以解决机器人主动推理用户意图问题 manipulation spatiotemporal vision-language-action
3 Stand, Walk, Navigate: Recovery-Aware Visual Navigation on a Low-Cost Wheeled Quadruped 面向低成本轮腿式机器人，提出可从跌倒中恢复的视觉导航系统 quadruped legged robot locomotion
4 OmniDexGrasp: Generalizable Dexterous Grasping via Foundation Model and Force Feedback OmniDexGrasp：基于Foundation Model和力反馈的通用灵巧抓取 manipulation dexterous hand dexterous manipulation
5 Seq-DeepIPC: Sequential Sensing for End-to-End Control in Legged Robot Navigation Seq-DeepIPC：面向腿式机器人导航的序列感知端到端控制模型 legged robot depth estimation ✅
6 Full-Dynamics Real-Time Nonlinear Model Predictive Control of Heavy-Duty Hydraulic Manipulator for Trajectory Tracking Tasks 提出一种重型液压机械臂全动力学实时非线性模型预测控制方法，用于轨迹跟踪任务。 model predictive control
7 TARC: Time-Adaptive Robotic Control 提出时间自适应机器人控制（TARC），解决固定频率控制的局限性 quadruped sim-to-real reinforcement learning
8 RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation RobotArena $\infty$: 通过真实到模拟转换实现可扩展的机器人基准测试 manipulation VLA
9 Combining High Level Scheduling and Low Level Control to Manage Fleets of Mobile Robots 提出高层调度与低层控制结合的两层框架，解决工业环境中移动机器人集群的动态协调问题。 MPC model predictive control
10 Awakening Facial Emotional Expressions in Human-Robot 提出基于KAN和注意力机制的端到端学习框架，用于类人机器人自主生成面部表情 humanoid humanoid robot
11 Workspace Registration and Collision Detection for Industrial Robotics Applications 针对工业机器人应用，提出工作空间注册与碰撞检测方案 motion planning
12 Planning Oriented Integrated Sensing and Communication 提出面向规划的集成感知与通信框架，提升自动驾驶安全性和效率 motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 Deductive Chain-of-Thought Augmented Socially-aware Robot Navigation World Model 提出NaviWM以解决社交机器人导航中的安全性与合理性问题 world model large language model chain-of-thought
14 Transferable Deep Reinforcement Learning for Cross-Domain Navigation: from Farmland to the Moon 提出基于DRL的跨域迁移导航方法，实现从农田到月球的零样本泛化 reinforcement learning deep reinforcement learning DRL
15 Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation 提出基于扩散策略和多时间尺度世界模型的深度主动推理框架，用于真实环境探索与导航。 diffusion policy world model
16 Never Too Rigid to Reach: Adaptive Virtual Model Control with LLM- and Lyapunov-Based Reinforcement Learning 提出基于LLM和Lyapunov强化学习的自适应虚拟模型控制，提升机器人臂在不确定环境下的适应性。 reinforcement learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
17 Dexbotic: Open-Source Vision-Language-Action Toolbox Dexbotic：开源视觉-语言-动作工具箱，助力具身智能研究 vision-language-action VLA foundation model
18 UrbanVLA: A Vision-Language-Action Model for Urban Micromobility 提出UrbanVLA，用于城市微出行场景下基于视觉-语言-动作的导航。 vision-language-action VLA
19 Large language model-based task planning for service robots: A review 综述：基于大语言模型的服务机器人任务规划研究进展 large language model multimodal
20 STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization STRIDER：通过指令对齐的结构化决策空间优化实现导航 VLN

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

#题目一句话要点标签🔗⭐
21 Explicit Memory through Online 3D Gaussian Splatting Improves Class-Agnostic Video Segmentation 通过在线3D高斯点云增强视频分割的记忆能力 3D gaussian splatting 3DGS gaussian splatting
22 Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments 提出自适应关键帧选择方法以解决动态环境中的3D重建问题 scene reconstruction

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

#题目一句话要点标签🔗⭐
23 HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment HyPerNav：利用混合感知实现未知环境中面向对象的导航 egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页