cs.RO（2025-10-11）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 It Takes Two: Learning Interactive Whole-Body Control Between Humanoid Robots Harmanoid：提出双人形机器人交互控制框架，实现高保真和物理真实的动作模仿。 humanoid humanoid robot whole-body control
2 ATRos: Learning Energy-Efficient Agile Locomotion for Wheeled-legged Robots ATRos：一种基于强化学习的轮腿机器人高效敏捷混合运动控制框架 legged robot legged locomotion whole-body control
3 Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review 综述强化学习在机器人与控制系统中的应用：分类、趋势与结构化回顾 locomotion manipulation reinforcement learning
4 Ctrl-World: A Controllable Generative World Model for Robot Manipulation 提出Ctrl-World，用于机器人操作的可控生成世界模型，提升策略学习。 manipulation world model instruction following
5 LLM-HBT: Dynamic Behavior Tree Construction for Adaptive Coordination in Heterogeneous Robots 提出动态行为树构建框架以解决异构机器人协调问题 legged robot large language model
6 Learning to Throw-Flip 提出一种基于学习的投掷翻转方法，实现机器人对物体精确的姿态控制 manipulation PULSE
7 A3RNN: Bi-directional Fusion of Bottom-up and Top-down Process for Developmental Visual Attention in Robots 提出A3RNN模型，通过双向融合自下而上和自上而下过程，实现机器人发育视觉注意力。 manipulation imitation learning
8 Rise of the Robochemist 机器人化学家：融合机器人与AI，革新化学实验范式 teleoperation

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

#题目一句话要点标签🔗⭐
9 X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model X-VLA：基于软提示Transformer的可扩展跨具身视觉-语言-动作模型 flow matching cross-embodiment vision-language-action ✅
10 UF-RNN: Real-Time Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction 提出UF-RNN，通过不确定性驱动的预测提升机器人实时自适应运动生成能力 imitation learning motion generation
11 Dejavu: Towards Experience Feedback Learning for Embodied Intelligence Dejavu：面向具身智能的经验反馈学习框架，提升部署后智能体性能 reinforcement learning vision-language-action VLA
12 Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework 提出基于SAC的深度强化学习框架，用于双阿克曼转向机器人的安全操控 reinforcement learning deep reinforcement learning SAC

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

#题目一句话要点标签🔗⭐
13 VG-Mapping: Variation-Aware 3D Gaussians for Online Semi-static Scene Mapping VG-Mapping：面向半静态场景的变异感知3D高斯在线建图 3D gaussian splatting 3DGS gaussian splatting ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 sqrtVINS: Robust and Ultrafast Square-Root Filter-based 3D Motion Tracking 提出基于平方根滤波的sqrtVINS，实现快速、鲁棒的三维运动跟踪。 motion tracking

⬅️ 返回 cs.RO 首页 · 🏠 返回主页