cs.RO（2026-03-24）

📊 共 17 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models	基于视觉-语言-动作模型的灵巧操作Sim-to-Real泛化经验研究	manipulation dexterous manipulation sim-to-real
2	SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation	提出SG-VLA模型，通过空间信息增强的视觉-语言-动作模型提升移动操作机器人性能	manipulation mobile manipulation imitation learning
3	VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs	提出VTAM：融合触觉信息的视频-动作模型，提升复杂物理交互性能	manipulation world model representation learning
4	Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring	Agile-VLA：基于隐式可供性锚定的少样本工业姿态校正	manipulation affordance vision-language-action
5	A Multimodal Framework for Human-Multi-Agent Interaction	提出多模态框架，实现人与多智能体在社会环境中的自然交互	humanoid humanoid robot locomotion
6	Instrument-Splatting++: Towards Controllable Surgical Instrument Digital Twin Using Gaussian Splatting	提出Instrument-Splatting++，利用高斯溅射实现可控高精度手术器械数字孪生。	real2sim 3D gaussian splatting 3DGS
7	CATNAV: Cached Vision-Language Traversability for Efficient Zero-Shot Robot Navigation	CATNAV：基于缓存的视觉-语言可通行性，实现高效的零样本机器人导航	quadruped traversability cross-embodiment
8	Learning Safe-Stoppability Monitors for Humanoid Robots	提出PRISM框架，学习人形机器人安全可停止性监测器	humanoid humanoid robot sim-to-real
9	Learning Multi-Agent Local Collision-Avoidance for Collaborative Carrying tasks with Coupled Quadrupedal Robots	提出基于强化学习的多智能体局部避障策略，用于耦合四足机器人的协同搬运任务	quadruped locomotion locomotion policy
10	Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation	E3Flow：基于球谐函数的SE(3)等变混合视觉运动流策略，提升机器人操作效率。	manipulation policy learning diffusion policy	✅
11	Path Planning and Reinforcement Learning-Driven Control of On-Orbit Free-Flying Multi-Arm Robots	提出轨迹优化与强化学习混合方法，用于在轨自由飞行多臂机器人的运动规划与控制。	trajectory optimization motion planning reinforcement learning
12	Learning Actuator-Aware Spectral Submanifolds for Precise Control of Continuum Robots	提出控制增强谱子流形，用于精确控制连续体机器人	MPC model predictive control SSM
13	Task-Aware Positioning for Improvisational Tasks in Mobile Construction Robots via an AI Agent with Multi-LMM Modules	提出基于多LMM模块AI代理的任务感知定位方法，用于移动建筑机器人的即兴任务	quadruped multimodal
14	PHANTOM Hand	PHANTOM Hand：结合精确控制与柔顺抓取的腱驱动灵巧手	manipulation motion planning
15	Human vs. NAO: A Computational-Behavioral Framework for Quantifying Social Orienting in Autism and Typical Development	提出计算行为框架，量化自闭症和典型发育儿童对人类和NAO机器人社交引导的差异。	humanoid humanoid robot

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

#	题目	一句话要点	标签	🔗	⭐
16	Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction	提出分离式后退视野策略，解决轨迹预测中可微仿真导致的短视问题。	differentiable simulation

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

#	题目	一句话要点	标签	🔗	⭐
17	Tightly-Coupled Radar-Visual-Inertial Odometry	提出一种紧耦合雷达-视觉-惯性里程计，提升弱光、低纹理环境下的鲁棒性。	VIO	✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页