cs.RO（2026-07-06）

📊 共 23 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) 支柱三：空间感知与语义 (Perception & Semantics) (4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 PRISM: Personalized Robotic Dataset Generation via Image-based Scene and Motion Synthesis 提出PRISM以解决个性化机器人数据集生成问题 manipulation teleoperation policy learning
2 DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation 提出DSWAM以解决机器人操作中的任务分解问题 manipulation world model world models
3 Athena-WBC: Capability-Aligned Policy Experts for Long-Tail Humanoid Whole-Body Control 提出Athena-WBC以解决长尾人形机器人全身控制问题 humanoid whole-body control motion tracking
4 KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation 提出KAM-WM框架以解决机器人操作中的视觉先验问题 manipulation diffusion policy flow matching
5 CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models 提出CAC-VLA以解决视觉-语言-动作模型的动作条件化问题 manipulation vision-language-action VLA
6 Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation 提出零-shot方法以解决多指灵巧手的现实差距问题 manipulation dexterous hand dexterous manipulation
7 Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning 提出简单到复杂的演示收集策略以提升VLA学习效率 manipulation dual-arm policy learning
8 Geometry-Aware Motion Latents for Learning Robust Manipulation Policies 提出GeoMoLa以解决机器人操作中的运动模式学习问题 manipulation motion latent
9 Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models 提出Deform360以解决可变形物体建模挑战 manipulation bi-manual world model
10 Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation 提出Cortex框架以解决长时间操作中的规划与执行问题 manipulation vision-language-action VLA
11 SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing 提出SILO框架以解决多阶段电缆布线的仿真到现实转移问题 manipulation sim-to-real reinforcement learning
12 GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks 提出GaP以解决变异自动化任务中的可靠性问题 motion planning task and motion planning TAMP ✅
13 InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization 提出InternVLA-A1.5以解决机器人操作中的语义与动态预测问题 manipulation world model world models
14 Aerial Manipulation: Contact, Medium Coupling, and the Geometry of Readiness 提出介质感知的空中操控方法以解决传统操控不足问题 locomotion manipulation
15 HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors 提出HUGS框架以解决多模式多尺度灵巧抓取问题 bi-manual

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
16 A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving 提出可靠的上下文感知与时间规划框架以解决自动驾驶安全问题 scene understanding motion prediction
17 Geometry-Aware Visual Odometry for Bronchoscopic Navigation via High-Gain Observer Fusion 提出几何感知视觉里程计以解决支气管镜导航问题 visual odometry
18 DIVO: Continuous-time DVL-Inertial-Visual Odometry for Unmanned Underwater Vehicles 提出连续时间DVL-惯性-视觉里程计以解决水下定位问题 visual odometry
19 WinTA-GIL: Windowed Trajectory Alignment for GNSS-IMU-LiDAR Heading Refinement in Intermittent Signal Environments 提出WinTA-GIL以解决GNSS-IMU-LiDAR环境下航向估计问题 LIO

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
20 Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning 提出基于Pinocchio的信实推理方法以提升机器人决策能力 reinforcement learning vision-language-action VLA ✅
21 SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies 提出SEAM以解决视觉-语言-动作策略中的动作块平滑执行问题 flow matching vision-language-action VLA
22 Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity 提出空间注意力机制以优化机器人动作执行时间 diffusion policy

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

#题目一句话要点标签🔗⭐
23 Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery 提出轨迹锚优化以解决过度自信的热视觉位置识别问题 geometric consistency foundation model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页