cs.RO（2025-11-21）

📊 共 21 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱三：空间感知 (Perception & SLAM) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Human Imitated Bipedal Locomotion with Frequency Based Gait Generator Network 提出基于频率的步态生成网络，结合PPO控制，实现类人双足稳健行走 bipedal biped locomotion
2 Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data AMS：融合异构数据，实现敏捷与稳定兼备的通用人形机器人控制 humanoid humanoid robot humanoid control
3 SM2ITH: Safe Mobile Manipulation with Interactive Human Prediction via Task-Hierarchical Bilevel Model Predictive Control SM²ITH：基于任务分层双层MPC的安全移动操作与交互式人类行为预测 manipulation mobile manipulation model predictive control
4 METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model METIS：多源自中心训练的集成灵巧视觉-语言-动作模型 manipulation dexterous manipulation teleoperation
5 RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation RoboCOIN：开源多形态双臂机器人操作数据集，促进集成操作学习 manipulation bi-manual bimanual manipulation ✅
6 Learning Diffusion Policies for Robotic Manipulation of Timber Joinery under Fabrication Uncertainty 提出基于扩散策略学习的木材榫卯结构机器人操作方法，解决装配不确定性问题 manipulation policy learning diffusion policy
7 See, Plan, Cut: MPC-Based Autonomous Volumetric Robotic Laser Surgery with OCT Guidance 提出RATS系统以解决现有机器人激光手术缺乏体积规划与反馈的问题 MPC model predictive control
8 H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation 提出H-GAR框架，通过目标驱动的观察-动作细化实现更精确的机器人操作 manipulation
9 Vector Cost Behavioral Planning for Autonomous Robotic Systems with Contemporary Validation Strategies 提出基于向量代价双矩阵博弈的机器人行为规划方法，提升多目标决策性能。 motion planning ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
10 HALO: High-Altitude Language-Conditioned Monocular Aerial Exploration and Navigation HALO：基于单目视觉和语言条件的高空无人机探索与导航 semantic mapping semantic map language conditioned ✅
11 Robot Confirmation Generation and Action Planning Using Long-context Q-Former Integrated with Multimodal LLM 提出基于长上下文Q-Former与多模态LLM的机器人动作确认与规划方法 scene understanding multimodal
12 TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making 提出TP-MDDN基准与AWMSystem系统，解决具身AI中多需求任务偏好导航问题 semantic mapping semantic map embodied AI
13 Vision-Guided Optic Flow Navigation for Small Lunar Missions 针对小型月球任务，提出一种基于视觉引导光流导航的轻量级自主导航方案 depth estimation optical flow

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

#题目一句话要点标签🔗⭐
14 Efficient Robot Design with Multi-Objective Black-Box Optimization and Large Language Models 提出基于LLM辅助黑盒优化的机器人高效设计方法 large language model
15 SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding SPEAR-1：通过3D理解扩展机器人演示学习能力 foundation model
16 FORWARD: Dataset of a forwarder operating in rough terrain 发布FORWARD数据集，用于林业机械在复杂地形下的感知、控制与仿真研究。 multimodal
17 Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation Progress-Think提出语义进度推理，提升视觉-语言导航任务的性能和效率。 vision-language-action

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

#题目一句话要点标签🔗⭐
18 RynnVLA-002: A Unified Vision-Language-Action and World Model RynnVLA-002：提出统一的视觉-语言-动作和世界模型，提升机器人任务性能。 world model vision-language-action VLA
19 Stable Offline Hand-Eye Calibration for any Robot with Just One Mark 提出CalibAll，仅用单标记实现任意机器人离线手眼标定的稳定方法 imitation learning foundation model

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

#题目一句话要点标签🔗⭐
20 IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation 提出IndustryNav：动态工业导航场景下具身智能体的空间推理基准 egocentric egocentric vision large language model

🔬 支柱三：空间感知 (Perception & SLAM) (1 篇)

#题目一句话要点标签🔗⭐
21 Single-Pixel Tactile Skin via Compressive Sampling 提出基于压缩感知的单像素触觉皮肤，解决大面积触觉传感的数据瓶颈问题 localization

⬅️ 返回 cs.RO 首页 · 🏠 返回主页