cs.RO（2025-09-12）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TASC: Task-Aware Shared Control for Teleoperated Manipulation	TASC：面向遥操作的、任务感知的共享控制，实现零样本泛化	manipulation shared control open-vocabulary	✅
2	Efficient Learning-Based Control of a Legged Robot in Lunar Gravity	提出基于强化学习的腿式机器人重力自适应控制方法，优化月球等低重力环境下的能耗。	legged robot legged locomotion locomotion
3	STL-Based Motion Planning and Uncertainty-Aware Risk Analysis for Human-Robot Collaboration with a Multi-Rotor Aerial Vehicle	提出基于STL的多旋翼人机协作运动规划与不确定性风险分析方法	motion planning
4	Coordinated Motion Planning of a Wearable Multi-Limb System for Enhanced Human-Robot Interaction	提出一种可穿戴多肢机器人的协同运动规划方法，降低人机交互力矩	motion planning
5	Prespecified-Performance Kinematic Tracking Control for Aerial Manipulation	针对空中机械臂，提出预设性能的末端执行器运动学跟踪控制方法	manipulation
6	Design and Evaluation of Two Spherical Systems for Mobile 3D Mapping	设计并评估两种用于移动3D地图构建的球形机器人系统	locomotion LIO
7	Towards simulation-based optimization of compliant fingers for high-speed connector assembly	提出基于仿真的柔性手指优化方法，提升高速连接器装配的鲁棒性	manipulation

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

#	题目	一句话要点	标签	🔗	⭐
8	DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning	DiffAero：用于高效四旋翼策略学习的GPU加速可微仿真框架	policy learning differentiable simulation	✅
9	GundamQ: Multi-Scale Spatio-Temporal Representation Learning for Robust Robot Path Planning	GundamQ：多尺度时空表征学习提升机器人鲁棒路径规划能力	reinforcement learning deep reinforcement learning representation learning

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

#	题目	一句话要点	标签	🔗	⭐
10	GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation	提出基于图约束优化的免训练视觉语言导航框架，解决真实场景泛化问题	spatial relationship VLN

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

#	题目	一句话要点	标签	🔗	⭐
11	Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States	提出一种基于LED状态分类的自监督视觉位姿估计方法，无需位姿标签。	depth estimation monocular depth

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Robot guide with multi-agent control and automatic scenario generation with LLM	提出基于LLM自动生成场景的多智能体导游机器人控制架构	large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页