cs.RO（2026-05-13）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 AttenA+: Rectifying Action Inequality in Robotic Foundation Models AttenA+：通过速度驱动的动作注意力，纠正机器人基础模型中的动作不平等性 manipulation vision-language-action VLA
2 What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models PAIR-VLA：通过视觉鲁棒强化学习微调VLA模型，提升机器人操作泛化性 manipulation reinforcement learning PPO
3 RotVLA: Rotational Latent Action for Vision-Language-Action Model RotVLA：基于旋转潜在动作的视觉-语言-动作模型，提升机器人控制性能。 manipulation flow matching cross-embodiment
4 Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels 提出基于强化学习的四足机器人隧道穿越方法，解决狭窄空间自主导航难题 quadruped locomotion reinforcement learning
5 TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video 提出TouchAnything框架与EgoTouch数据集，用于从第一视角视频中估计双手动触觉信息。 manipulation bi-manual human-object interaction
6 FrameSkip: Learning from Fewer but More Informative Frames in VLA Training FrameSkip：通过视觉-语言-动作训练中更少但信息量更大的帧进行学习 manipulation teleoperation vision-language-action
7 MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots MUJICA：用于轮腿机器人的多技能统一联合控制架构，提升复杂地形适应性 legged robot locomotion sim-to-real
8 CUBic: Coordinated Unified Bimanual Perception and Control Framework CUBic：提出一种统一的双手操作感知与控制框架，提升协调性和任务成功率。 manipulation bi-manual bimanual manipulation
9 SID: Sliding into Distribution for Robust Few-Demonstration Manipulation 提出SID框架以解决少量演示下的鲁棒性操控问题 manipulation flow matching egocentric
10 SECOND-Grasp: Semantic Contact-guided Dexterous Grasping SECOND-Grasp：语义引导的灵巧抓取框架，提升稳定性和语义理解 manipulation policy learning geometric consistency
11 RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data RoboEvolve：面向数据稀缺的机器人操作，共进化规划器-模拟器 manipulation
12 Manipulation Planning for Construction Activities with Repetitive Tasks 提出基于虚拟现实示教的重复性建筑任务操作技能学习方法 manipulation
13 Beyond VMAF: Towards Application-Specific Metrics for Teleoperation Video 针对远程操控视频，提出领域自适应的VMAF质量评估指标 teleoperation
14 Object Manipulation of the Variable Topology Truss system 针对变胞桁架系统的混合控制物体操作策略 manipulation
15 When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation 提出基于episode相对坐标系的机器人状态编码，提升操作任务的鲁棒性 manipulation
16 TinySDP: Real Time Semidefinite Optimization for Certifiable and Agile Edge Robotics TinySDP：用于可认证和敏捷边缘机器人的实时半定规划求解器 MPC motion planning SAC
17 Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach 提出基于安全滤波的分布鲁棒控制方法，解决任意不确定性下的非线性系统安全问题 trajectory optimization

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
18 Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models 提出VLAs-as-Tools以解决长时间任务中的机器人执行问题 vision-language-action VLA instruction following
19 Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs Realtime-VLA FLASH：用于扩散VLA的推测推理框架，加速实时部署 vision-language-action VLA
20 HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation 提出HCSG框架，用于动态人机交互场景下基于语义-几何推理的视觉-语言导航。 VLN ✅

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

#题目一句话要点标签🔗⭐
21 Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models 提出GTA-VLA框架，通过交互式视觉引导增强具身智能体的推理能力 affordance vision-language-action VLA ✅
22 LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction LEXI-SG：基于单目RGB相机的房间引导前馈重建三维场景图构建 scene understanding open-vocabulary open vocabulary ✅

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

#题目一句话要点标签🔗⭐
23 BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning BlockVLA：通过块扩散微调加速自回归VLA模型推理 diffusion policy vision-language-action VLA

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

#题目一句话要点标签🔗⭐
24 What Limits Vision-and-Language Navigation ? 提出StereoNav，增强视觉语言导航中跨域空间定位的鲁棒性 egocentric vision-language-action VLN ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页