cs.RO（2026-08-03）

📊 共 31 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (24 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (24 篇)

#题目一句话要点标签🔗⭐
1 Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation 提出全景感知VLA以解决移动操控中的视觉局限问题 manipulation mobile manipulation bi-manual
2 StableMimic: Smooth Human-Like Recovery for Humanoid Motion Tracking - Learning Beyond the Tracking Distribution for Structured Post-Fall Behavior 提出StableMimic以解决类人机器人跌倒后的恢复问题 humanoid motion tracking Unitree
3 Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped Locomotion 提出Open-DiffLoco以解决盲四足机器人运动控制问题 quadruped locomotion locomotion policy
4 ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation 提出ChainVLA以解决长时间操作中的查询连贯性问题 manipulation vision-language-action VLA
5 Teleopit: A Full-Embodiment Humanoid Teleoperation System 提出Teleopit以解决类人机器人远程操作的协调控制问题 humanoid locomotion manipulation ✅
6 Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies 提出多视角统一相机场以解决RGB-only多相机VLA策略问题 humanoid manipulation metric depth
7 ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction 提出ReTouch以解决触觉反馈在灵巧操作中的整合问题 manipulation dexterous manipulation vision-language-action
8 AffordTrajDP: Dynamic Affordance-Guided Visuomotor Policy Learning for Robotic Manipulation 提出AffordTrajDP以解决静态可供性在机器人操作中的不一致问题 manipulation policy learning imitation learning
9 TRACE: Ergodic Trajectory Optimization for Active Scene Reconstruction 提出TRACE以解决主动场景重建中的轨迹优化问题 trajectory optimization gaussian splatting splatting ✅
10 Perception-and-action system for humanoid robot task execution in construction 提出感知与行动系统以解决人形机器人在建筑任务中的执行问题 humanoid humanoid robot motion tracking
11 Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models 提出GSR方法以解决视觉-语言-动作模型的指令泛化问题 manipulation vision-language-action VLA
12 Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models 提出AtVLA框架以解决视觉-语言-动作模型的空间感知问题 manipulation vision-language-action VLA
13 Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models 提出黑箱框架以解决视觉-语言-动作模型中的位置盲点问题 manipulation vision-language-action VLA
14 World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous Deployment 提出异步部署策略以解决机器人执行中的延迟问题 manipulation bi-manual world action model
15 Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data 提出Ego2Robot以解决机器人数据合成问题 manipulation egocentric vision-language-action ✅
16 Residual-Based Adaptive Kalman Filtering for Legged Robot State Estimation 提出基于残差的自适应卡尔曼滤波以解决腿式机器人状态估计问题 quadruped legged robot Unitree
17 TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning 提出TWINS系统以解决身体接触操控学习问题 manipulation dual-arm imitation learning ✅
18 Bridging the Sim-to-Real Gap in Parallel-Link Leg Mechanisms via Simulator-Side Dynamics Normalization 提出S3N方法以解决并联机构仿真与现实间的动态差距问题 locomotion sim-to-real
19 Situation Aware Frontier Prioritization for Quadruped Search and Rescue 提出情境感知前沿优先级方法以优化四足机器人救援任务 quadruped
20 Toward Geometry-Scalable Whole-Body Touch for Humanoids: A 3D-Printed Conformal EIT Skin 提出几何可扩展的全身触觉传感皮肤以解决人形机器人触觉覆盖问题 humanoid
21 CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs 提出CoWAM以优化双手机器人策略的选择性干预 bi-manual world action model world action models
22 Probabilistic Reachable-Action Verification of Visuomotor Policies via Set-Based Training 提出基于集合训练的可达动作验证方法以解决视觉运动策略问题 manipulation
23 Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data 提出一种新方法以解决模型不匹配下的计划认证问题 sim-to-real
24 Hybrid Impedance-Admittance Control with Multi-Link Aerial Robot for Contact-Rich Surface Sliding Task 提出混合阻抗-导纳控制以解决多链 aerial 机器人接触丰富的表面滑动问题 manipulation

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

#题目一句话要点标签🔗⭐
25 TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks 提出TravKAN以解决自主移动机器人可通行性分析问题 traversability
26 TANGO-VIO: Triangulation-Aware Navigation with Guaranteed Feature-Observability for Visual-Inertial Odometry 提出TANGO-VIO以解决视觉惯性里程计中的特征可观测性问题 VIO
27 FRA-NBV: A Fast and Reflectivity-Aware Next-Best-View Strategy 提出FRA-NBV以解决反射表面对3D重建的影响 3D reconstruction

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

#题目一句话要点标签🔗⭐
28 Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills 提出机器人学习技术分类以解决自我改进问题 reinforcement learning cross-embodiment vision-language-action
29 A Forward-Inverse Dynamic Game Framework for Enhanced Multi-Agent Trajectory Planning 提出KL正则化动态博弈框架以增强多智能体轨迹规划 reinforcement learning inverse reinforcement learning

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

#题目一句话要点标签🔗⭐
30 MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping 提出MANGO-Grasp以解决跨实体灵巧抓取问题 cross-embodiment ✅

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

#题目一句话要点标签🔗⭐
31 ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions 提出ProtoAct以解决生物实验室协议转化为机器人动作的问题 VLA large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页