cs.RO（2026-06-16）

📊 共 22 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models 提出Qwen-RobotManip以解决机器人操作中的数据异质性问题 manipulation egocentric human-to-robot
2 MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation 提出MuseVLA以解决机器人多模态感知不足问题 manipulation dexterous hand vision-language-action
3 HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning 提出HumanoidArena以解决人形机器人层次化学习问题 humanoid humanoid robot policy learning
4 ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation 提出ThinkingVLA以解决机器人操作中的视觉与语言推理问题 manipulation spatial relationship vision-language-action
5 WireCraft: A Simulation Benchmark for Industrial DLO Manipulation 提出WireCraft以解决工业DLO操作的基准测试问题 manipulation dexterous manipulation reinforcement learning
6 GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments 提出GASE以解决高保真仿真环境重建问题 manipulation sim-to-real gaussian splatting
7 Uncertainty Quantification for Flow-Based Vision-Language-Action Models 提出一种不确定性量化方法以提升流基视觉-语言-动作模型的可靠性 manipulation flow matching vision-language-action
8 LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation 提出LAGO Policy以解决异步推理下的平滑操作问题 manipulation trajectory optimization diffusion policy
9 Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework 提出多模态边缘计算框架以解决异构移动机器人上的无接触呼吸监测问题 quadruped locomotion multimodal
10 EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies 提出EBench以诊断通用移动操控策略的能力 manipulation mobile manipulation
11 AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation 提出AnnotateAnything以解决3D资产自动标注问题 manipulation affordance affordance detection
12 WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT 提出WAM-RL以解决世界-动作模型在训练中的局限性问题 manipulation reinforcement learning world model
13 DexLink Hand: A Compact, Affordable, 16-DOF Linkage-Driven Hand with Human-Like Dexterity 提出一种紧凑且经济的16自由度机械手以解决灵巧性与成本的平衡问题 manipulation dexterous manipulation teleoperation
14 When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning 提出睡眠机器人框架以解决共享策略下的技能整合问题 shared control reinforcement learning imitation learning
15 EgoInfinity: A Web-Scale 4D Hand-Object Interaction Data Engine for Any-View Robot Retargeting and Video-to-Action Robot Learning 提出EgoInfinity以解决视频转机器人训练数据的瓶颈问题 manipulation cross-embodiment
16 Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies 提出LeaP以优化生成机器人策略的起始分布 manipulation flow matching
17 Beyond Failure Recovery: An Engagement-Aware Human-in-the-loop Framework for Robotic Systems 提出E-MPC框架以提升人机交互中的用户参与感 MPC

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

#题目一句话要点标签🔗⭐
18 PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space 提出PearlVLA以解决VLA模型的高延迟与低效能问题 world model world models vision-language-action
19 Embodiment Shapes Rolling Behavior in a Multimodal Infant Model 提出多模态虚拟婴儿模型MIMo以研究滚动行为 reinforcement learning multimodal

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
20 ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI 提出ERQA-Plus以解决现有嵌入式AI推理基准不足的问题 embodied AI visual grounding ✅
21 MagicSim: A Unified Infrastructure for Executable Embodied Interaction 提出MagicSim以统一机器人学习中的可执行交互环境 multimodal

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

#题目一句话要点标签🔗⭐
22 EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning 提出EAGG以解决跨端执行器抓取生成问题 cross-embodiment ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页