cs.RO（2026-06-12）

📊 共 80 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (59 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (11) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱六：视频提取与匹配 (Video Extraction) (2)

🔬 支柱一：机器人控制 (Robot Control) (59 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 Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning 提出盲抓取框架以解决触觉信号稀疏问题 manipulation dexterous hand sim-to-real
3 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
4 WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning 提出WT-UMI以解决全身机器人在接触感知中的挑战 humanoid manipulation whole-body manipulation
5 Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning 提出GRASP框架以解决机器人自然语言理解问题 manipulation motion planning open-vocabulary
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 Mana: Dexterous Manipulation of Articulated Tools 提出Mana框架以解决关节工具灵巧操作问题 manipulation dexterous manipulation in-hand manipulation
8 RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning 提出RoboNaldo以解决人形机器人足球射门的稳定性与准确性问题 humanoid motion tracking locomotion
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 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
11 AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly 提出AssemLM以解决机器人组装中的空间推理问题 manipulation large language model multimodal
12 $\texttt{WEAVER}$, Better, Faster, Longer: An Effective World Model for Robotic Manipulation 提出WEAVER以解决机器人操控中的世界模型挑战 manipulation flow matching world model
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 EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations 提出EgoEngine以解决人类视频到机器人演示的转换问题 manipulation dexterous manipulation policy learning
15 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
16 Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration 提出基于模仿学习的协作VLA模型以解决人机协作中的提前辅助问题 manipulation imitation learning vision-language-action
17 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
18 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
19 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
20 Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants 提出Y-BotFrame框架以提升四足机器人助手的智能交互能力 quadruped large language model multimodal
21 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
22 RGB-S: Image-Aligned Tactile Saliency for Robust Dexterous Manipulation 提出RGB-S框架以解决视觉信息不可靠下的触觉感知问题 manipulation dexterous manipulation
23 UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data 提出UniDexTok以解决灵巧手状态表示碎片化问题 manipulation dexterous hand cross-embodiment
24 Action-Effect Memory Pretraining for Robot Manipulation 提出AEM框架以提升机器人操作的记忆能力 manipulation diffusion policy Mamba
25 Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation 提出Sparse2Act以解决稀疏3D表示在跨域机器人操作中的局限性 manipulation sim-to-real
26 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
27 Foresight: Iterative Reasoning About Clues that Matter for Navigation 提出Foresight框架以解决开放世界无地图导航问题 motion planning reinforcement learning foundation model
28 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中的过程理解问题 manipulation
29 FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation 提出FTP-1以解决触觉传感器间通用性不足的问题 manipulation
30 Lexicographic Minimum-Violation Motion Planning using Signal Temporal Logic 提出基于信号时序逻辑的最小违反运动规划方法 motion planning
31 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
32 Improving Robotic Generalist Policies via Flow Reversal Steering 提出流反转引导以提升机器人通用策略的性能 manipulation reinforcement learning flow matching
33 Active Semantic Perception 提出主动语义感知方法以解决室内环境探索问题 Unitree large language model
34 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混乱环境中的顺序物体抓取问题 manipulation
35 Learning Robot Safety from Sparse Human Feedback using Conformal Prediction 提出基于稀疏人类反馈的机器人安全学习方法 model predictive control
36 Adaptive Model-Predictive Control of a Soft Continuum Robot Using a Physics-Informed Neural Network Based on Cosserat Rod Theory 提出基于物理信息神经网络的软连续机器人自适应模型预测控制方法 MPC
37 Adaptive-Horizon Conflict-Based Search for Closed-Loop Multi-Agent Path Finding 提出ACCBS算法以解决多智能体路径规划问题 MPC
38 Robust Fall Recovery for Armless Bipedal-Wheeled Robots Via Force-Guided Learning 提出基于力引导学习的无臂双足轮式机器人跌倒恢复方法 quadruped legged robot legged locomotion ✅
39 Whole-Body Impedance Model Predictive Control for Safe Physical Human--Robot Interaction on Floating-Base Platforms 提出全身阻抗模型预测控制以解决浮动基座机器人安全人机交互问题 humanoid biped whole-body control
40 Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models 提出弹性查询强化学习以优化VLA模型的执行效率 manipulation reinforcement learning vision-language-action
41 Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation 提出CORD-SLS以解决安全变形物体操控问题 manipulation MPC model predictive control
42 ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation 提出ReactVLA以解决机器人操控中的低延迟问题 manipulation vision-language-action VLA ✅
43 Impedance MPC with Disturbance Estimation for Dexterous Hand Control 提出阻抗模型预测控制以解决灵巧手控制中的接触问题 dexterous hand MPC model predictive control
44 Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing 提出选择性扩散噪声以解决机器人操作中的脆弱性问题 manipulation vision-language-action VLA
45 Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motions 提出Kine2Go数据集以解决Unitree Go2机器人运动数据获取难题 quadruped locomotion Unitree
46 Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera 提出空间条件扩散策略以解决单摄像头操控精度问题 manipulation imitation learning diffusion policy
47 Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback 提出通用操作外骨骼以解决家庭环境中的安全操作问题 manipulation mobile manipulation bi-manual
48 ORCA: A Platform for Open-Source Dexterity Research 提出ORCA平台以推动开放源代码的灵巧机器人研究 manipulation dexterous hand dexterous manipulation
49 Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency 提出统一安全强化学习框架以解决自主高速驾驶安全与效率问题 MPC reinforcement learning deep reinforcement learning
50 A Modular Dual-Arm Apple Harvesting Robot with Enhanced Field Performance 提出模块化双臂苹果采摘机器人以解决果园劳动力短缺问题 dual-arm foundation model
51 EgoGuide: Egocentric Guidance for Efficient Robot-Free Demonstration Collection and Learning 提出EgoGuide以解决机器人学习数据收集效率低下问题 manipulation egocentric ✅
52 Short-Horizon Position Accuracy of Single-Track Models: Implications for Motion Planning of Autonomous Vehicles 评估单轨模型短期位置精度以优化自动驾驶车辆运动规划 model predictive control motion planning
53 GAIT: Legged Robot Proprioceptive State Estimation with Attention over Inertial-Leg Tokens 提出基于注意力机制的IL标记化方法以提升腿式机器人自我感知状态估计 legged robot Unitree
54 The N2D Haptic Glove: A Multi-Finger Glove for 2D Directional Force Feedback for Contact Rich Manipulation 提出N2D触觉手套以解决单轴触觉反馈不足问题 manipulation teleoperation ✅
55 Semidefinite Relaxations for Collision-Free Motion Planning 提出半正定松弛方法以解决无碰撞运动规划问题 motion planning
56 SyLink Hand: A Synergy-Inspired Linkage-Driven Anthropomorphic Hand for Human-Like Dexterity 提出SyLink手以解决类人机器人手的灵活性与机械简化问题 manipulation dexterous hand
57 Sensitivity Shaping for Latent Modeling 提出支持条件控制敏感性正则化以解决动态模型中的OOD检测问题 manipulation
58 TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation 提出TRACE以解决延迟证据视觉运动模仿问题 manipulation ✅
59 AERMANI-PLACE: Language Guided Object Placement with Aerial Manipulators 提出AERMANI-PLACE以解决无人机物体放置的交互难题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
60 G-MAPP: GPU-accelerated Multi-Agent Planning and Perception for Reactive Motion Generation 提出G-MAPP以解决动态环境中的反应式运动生成问题 world model world models motion generation
61 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
62 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
63 EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence 提出EWAM以解决闭环在线适应问题 world action model world action models
64 Real-Time Execution with Autoregressive Policies 提出自回归策略以实现实时执行问题的解决方案 diffusion policy flow matching vision-language-action
65 From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation 提出FlowPilot以解决长距离人行道导航中的社会合规性问题 imitation learning flow matching preference learning
66 DrivingAgent: Design and Scheduling Agents for Autonomous Driving Systems 提出DrivingAgent以解决自主驾驶系统设计与调度问题 reinforcement learning large language model foundation model
67 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
68 ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving 提出ReactSim-Bench以评估自动驾驶中的反应能力 world model world models
69 Optimality-Preserving Decomposition for Scalable QAOA in Natural-Language-Guided Multi-Drone Assignment 提出一种优化保持分解方法以解决多无人机任务分配问题 DPO direct preference optimization large language model
70 FloVerse: Floor Plan-Guided Multi-Modal Navigation 提出FloVerse以解决多模态导航中的空间先验问题 imitation learning multimodal

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
71 SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models 提出SCALE以解决视觉-语言-动作模型的适应性执行问题 vision-language-action VLA
72 Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer Interfaces: A Proof of Concept Exploration 提出基于非侵入性BCI的多模态多智能体认知对齐框架以解决人机交互中的认知负荷问题 large language model
73 Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack 提出HyVLA-0.5以构建完整的机器人学习系统 vision-language-action VLA
74 When and How Severely: Scenario-Specific Safety Envelopes for Driving VLAs 提出场景特定安全包以解决VLA驾驶规划的安全认证问题 vision-language-action VLA
75 What Robots Do Matters More Than What They Look Like: Task Context Shapes Trust in Educational HRI 探讨任务背景对教育机器人信任的影响 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
76 Safety Case Patterns for VLA-based driving systems: Insights from SimLingo 提出RAISE方法以确保VLA驾驶系统的安全性 scene understanding vision-language-action VLA
77 DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management 提出DiskChunGS以解决3D高斯SLAM的内存限制问题 3D gaussian splatting 3DGS gaussian splatting
78 SplatlessDF: Continuous Distance Field Mapping with Non-Splatting Gaussians 提出SplatlessDF以解决高效距离场映射问题 gaussian splatting splatting

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
79 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
80 EgoMoD: Predicting Global Maps of Dynamics from Local Egocentric Observations 提出EgoMoD以解决动态环境中导航预测问题 egocentric zero-shot transfer

⬅️ 返回 cs.RO 首页 · 🏠 返回主页