cs.RO（2026-05-07）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation	提出OA-WAM，通过对象可寻址的世界动作模型提升机器人操作的鲁棒性。	manipulation flow matching world action model
2	DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions	DexSynRefine：合成与优化人-物交互运动，实现物理可行的灵巧机器人操作	manipulation dexterous manipulation sim-to-real
3	MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation	MaMi-HOI：协调全局运动学与局部几何，生成逼真的人-物交互	manipulation human-object interaction HOI	✅
4	ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting	ReActor：基于强化学习的物理感知运动重定向方法	quadruped reinforcement learning imitation learning
5	Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation	VISER：面向视觉真实感仿真的机器人操作评估基准	manipulation sim-to-real physically plausible
6	VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts	VLA-GSE：通过广义和专用专家提升VLA中的参数高效微调	manipulation vision-language-action VLA	✅
7	AssistDLO: Assistive Teleoperation for Deformable Linear Object Manipulation	AssistDLO：面向可变形线性物体操作的辅助遥操作框架	manipulation bi-manual teleoperation
8	RobotEQ: Transitioning from Passive Intelligence to Active Intelligence in Embodied AI	RobotEQ：构建具身AI主动智能基准，评估模型在社会规范理解与遵守能力	manipulation egocentric embodied AI
9	CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models	提出CKT-WAM，通过上下文知识迁移实现异构世界行动模型的参数高效泛化。	manipulation world action model world action models	✅
10	On the Emergence of Pendular Structure in Multi-Contact Locomotion	揭示多接触运动中摆动结构的涌现，优化角动量惩罚实现类LIPM控制	quadruped legged locomotion locomotion
11	When to Trust Imagination: Adaptive Action Execution for World Action Models	提出FFDC自适应世界行为模型执行，提升机器人操作的鲁棒性和效率	manipulation world action model world action models
12	Cycle-resolved Cephalopod-Inspired Pulsed-Jet Robot With High-Volume Expulsion and Drag-Reduced Gliding	提出周期解析的头足类仿生脉冲喷射机器人，实现大体积喷射和低阻力滑行	locomotion PULSE
13	Multi-Robot Coordination in V2X Environments	提出V2X通信框架，实现复杂城市交通环境中多机器人分散式协作	quadruped humanoid humanoid robot
14	TouchDrive: Electronics-Free Tactile Sensing Interface for Assistive Grasping	TouchDrive：一种用于辅助抓取的无电子触觉传感界面	manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
15	GA3T: A Ground-Aerial Terrain Traversability Dataset for Heterogeneous Robot Teams in Unstructured Environments	提出GA3T数据集以解决异构机器人团队在非结构化环境中的感知问题	scene understanding traversability
16	Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation	提出即插即用标签图扩散模型，解决通用目标导向导航中地图补全与语义一致性问题。	semantic map

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

#	题目	一句话要点	标签	🔗	⭐
17	Cross-Modal Navigation with Multi-Agent Reinforcement Learning	提出CRONA多智能体强化学习框架，用于跨模态导航任务。	reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页