cs.RO（2025-03-17）

📊 共 18 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 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation 提出Affordance引导的自洽MLLM，解决指令跟随操作中的跨模态干扰和几何可行性问题 manipulation affordance large language model ✅
2 MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation MoManipVLA：迁移视觉-语言-动作模型至通用移动操作 manipulation mobile manipulation motion planning
3 Humanoids in Hospitals: A Technical Study of Humanoid Robot Surrogates for Dexterous Medical Interventions 提出基于宇树G1人形机器人的遥操作系统，探索其在医疗干预中的应用潜力 humanoid humanoid robot bi-manual
4 Humanoid Policy ~ Human Policy 提出Human Action Transformer，利用人类第一视角数据提升人形机器人操作策略 humanoid humanoid robot manipulation
5 16 Ways to Gallop: Energetics and Body Dynamics of High-Speed Quadrupedal Gaits 分析多种奔跑步态能量学，优化四足机器人高速运动 quadruped legged robot locomotion
6 FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation FLEX框架：学习机器人无关的力控技能，用于持续接触的物体操作 manipulation reinforcement learning imitation learning ✅
7 HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learning HybridGen：VLM引导的混合规划方法，用于可扩展的模仿学习数据生成 manipulation imitation learning
8 Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach 提出基于在线示教的主动强化学习策略迁移方法，提升机器人泛化能力。 sim-to-real reinforcement learning
9 Transformable Modular Robots: A CPG-Based Approach to Independent and Collective Locomotion 提出基于CPG的模块化机器人控制方法，实现独立和协同运动 locomotion
10 Does the Appearance of Autonomous Conversational Robots Affect User Spoken Behaviors in Real-World Conference Interactions? 研究表明：类人机器人外形影响用户在会议互动中的口语行为 humanoid
11 Dense Policy: Bidirectional Autoregressive Learning of Actions 提出Dense Policy双向自回归学习动作，提升机器人操作策略。 manipulation
12 LIVEPOINT: Fully Decentralized, Safe, Deadlock-Free Multi-Robot Control in Cluttered Environments with High-Dimensional Inputs LIVEPOINT：一种完全去中心化、安全、无死锁的多机器人控制框架 MPC
13 In vivo validation of Wireless Power Transfer System for Magnetically Controlled Robotic Capsule Endoscopy 针对磁控胶囊内窥镜，提出一种无线电力传输系统，实现体内验证。 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
14 INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations INPROVF：利用大语言模型修复机器人高层控制器的假设违例问题 large language model
15 Multi-Touch and Bending Perception Using Electrical Impedance Tomography for Robotics 提出基于EIT的机器人多点触控与弯曲感知框架，解决形变干扰问题 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
16 MindEye-OmniAssist: A Gaze-Driven LLM-Enhanced Assistive Robot System for Implicit Intention Recognition and Task Execution MindEye-OmniAssist：基于注视驱动和LLM增强的辅助机器人系统，用于隐式意图识别和任务执行 open-vocabulary open vocabulary large language model

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

#题目一句话要点标签🔗⭐
17 Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot 在真实机器人Franka Emika Panda上，异步强化学习比同步强化学习更快更有效。 reinforcement learning

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

#题目一句话要点标签🔗⭐
18 Free-form language-based robotic reasoning and grasping 提出FreeGrasp，利用VLM解决自由文本引导的机器人抓取推理问题 spatial relationship ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页