cs.RO（2026-06-11）

📊 共 38 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (27 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (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) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (27 篇)

#题目一句话要点标签🔗⭐
1 Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids 提出Stubborn框架以解决人形机器人运动跟踪与跌倒恢复问题 humanoid motion tracking fall recovery ✅
2 SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation 提出SERF以解决长时间移动操作中的环境推理问题 manipulation mobile manipulation egocentric
3 WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning 提出WT-UMI以解决全身机器人操控中的接触力调节问题 humanoid manipulation whole-body manipulation ✅
4 Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning 提出GRASP框架以解决机器人语言理解与抓取任务问题 manipulation motion planning open-vocabulary
5 Mana: Dexterous Manipulation of Articulated Tools 提出Mana框架以解决关节工具的灵巧操控问题 manipulation dexterous manipulation in-hand manipulation
6 See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation 提出双层结构分解以解决双手机器人操控中的视觉与交互问题 manipulation bi-manual bimanual manipulation
7 PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation 提出PhysVLA以解决机器人操控中的物理知识缺失问题 manipulation vision-language-action VLA
8 Proprioceptive-visual correspondence enables self-other distinction in humanoid robots 提出自我与他者区分方法以解决人形机器人社交智能问题 humanoid humanoid robot motion planning ✅
9 GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training 提出GenHOI以解决人形机器人与物体交互的挑战 humanoid humanoid robot bi-manual
10 $\texttt{WEAVER}$, Better, Faster, Longer: An Effective World Model for Robotic Manipulation 提出WEAVER以解决机器人操作中的世界模型问题 manipulation flow matching world model ✅
11 ContactWorld: What Matters in Vision-Tactile World Models for Contact-Rich Manipulation 提出ContactWorld以解决接触丰富操控中的世界建模问题 manipulation world model world models
12 $μ_0$: A Scalable 3D Interaction-Trace World Model 提出$μ_0$以解决机器人学习中的可扩展性问题 manipulation world model world models
13 GIVE: Grounding Human Gestures in Vision-Language-Action Models 提出GIVE以解决人机交互中手势理解不足的问题 manipulation vision-language-action VLA
14 AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots 提出AIR-VLA+以解决无人机运动与操作耦合问题 manipulation flow matching VLA
15 GeoHAT: Geometry-Adaptive Hybrid Action Transformer for Mobile Manipulation 提出GeoHAT以解决移动操控中的几何感知与动作生成问题 manipulation mobile manipulation foundation model
16 EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation 提出EA-WM框架以解决长时间操作中的事件感知问题 manipulation world model world models
17 Trajectory-Level Redirection Attacks on Vision-Language-Action Models 提出轨迹级重定向攻击以揭示VLA模型的脆弱性 manipulation vision-language-action VLA
18 MCR-Bionic Hand: Anatomical Structural Priors for Dexterous Manipulation 提出MCR-Bionic手以解决灵巧机器人手的控制问题 manipulation dexterous manipulation
19 Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants 提出Y-BotFrame以解决四足机器人智能助手的模块化与交互问题 quadruped large language model multimodal ✅
20 Efficient Domain-Adaptive Policy Learning via Kernel Representation with Application to Quadrotor Control under Non-Stationary Disturbances 提出高效领域自适应策略学习算法以解决四旋翼控制中的非平稳干扰问题 sim-to-real policy learning differentiable simulation
21 SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale 提出SPARC框架以解决机器人演示标注可靠性问题 manipulation motion planning foundation model
22 FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation 提出FTP-1以解决触觉传感器通用性不足的问题 manipulation
23 RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation 提出RoboProcessBench以解决视觉语言机器人操作过程理解不足的问题 manipulation ✅
24 Redesigning Regularization for Effective Policy Smoothing 提出新正则化设计以有效平滑强化学习策略 quadruped sim-to-real reinforcement learning
25 An Attention-based Model for Robust Forecasting with Missing Modality 提出基于注意力的模型以解决缺失模态的鲁棒预测问题 manipulation multimodal
26 Improving Robotic Generalist Policies via Flow Reversal Steering 提出流反向引导以改善机器人通用策略 manipulation reinforcement learning flow matching
27 Towards Reliable Sequential Object Picking in Clutter: The Runner-up Solution to RGMC 2025 提出集成硬件软件管道以解决杂乱环境中的顺序物体抓取问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
28 NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation 提出NavWAM以解决目标导向视觉导航中的控制问题 world model world models world action model ✅
29 Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning 提出输出级正则化以消除单GPU VLA微调中的种子彩票问题 JEPA vision-language-action VLA
30 Multi-Agent Embodied Autonomous Driving: From V2X Information Exchange to Shared World Models 提出共享世界模型以解决多智能体自主驾驶中的协作问题 world model world models foundation model
31 EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment 提出EmbodiSteer以解决机器人模仿学习中的身体特异性问题 policy learning imitation learning cross-embodiment ✅
32 FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift 提出FlowMo-WM以解决水面车辆运动预测问题 world model world models
33 Real-Time Execution with Autoregressive Policies 通过调整自回归策略实现实时执行以解决延迟问题 diffusion policy flow matching vision-language-action
34 Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer 提出RepMT-SAC框架以解决多任务强化学习中的知识共享问题 reinforcement learning SAC

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
35 Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes 探讨幽默风格与话题对机器人幽默接受度的影响 HuMoR large language model

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

#题目一句话要点标签🔗⭐
36 AnyGoal: Vision-Language Guided Multi-Agent Exploration for Training-Free Lifelong Navigation 提出AnyGoal以解决多机器人无训练导航问题 open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
37 Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer Interfaces: A Proof of Concept Exploration 提出基于非侵入式BCI的多模态多智能体认知对齐框架以提升人机交互 large language model

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

#题目一句话要点标签🔗⭐
38 Scalable Dynamic Tactile Sensing Enabled by Passive and Flexible Acoustic Waveguides 提出基于被动柔性声波导的动态触觉传感技术以解决大面积传感器的灵活性与成本问题 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页