cs.RO（2026-07-08）

📊 共 28 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (18 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (18 篇)

#题目一句话要点标签🔗⭐
1 Immersive Social Interaction with VR and LLM-Assisted Humanoids 提出沉浸式社交互动框架以解决远程人形机器人操作难题 humanoid humanoid robot humanoid control
2 Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report 提出ABot-C0以解决四足机器人运动控制的可扩展性问题 quadruped humanoid humanoid control
3 TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation 提出TouchWorld以解决灵巧操作中的触觉反馈问题 manipulation dexterous manipulation world model
4 Compositional Motion Generation from Demonstration with Object-Centric Neural Fields 提出基于对象中心神经场的生成学习框架以实现机器人运动生成 manipulation motion generation
5 Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation 提出LaMem-VLA框架以解决长时间依赖的机器人操作问题 manipulation vision-language-action VLA
6 EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI 提出EmbodiedGen V2以解决可执行仿真环境构建问题 manipulation mobile manipulation reinforcement learning
7 Smooth Operator: A Real-Time Sampling-Based Algorithm for Kinematic Hand Retargeting 提出SBR算法以解决现有手部重定向中的抖动问题 manipulation dexterous manipulation teleoperation
8 Disturbance-aware Motion Planning for Over-actuated Underwater Vehicles Exploiting Actuation Redundancy for High-fidelity 3D Reconstruction 提出基于冗余驱动的干扰感知运动规划以提高水下机器人3D重建精度 motion planning 3D reconstruction
9 A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation 提出层级闭环多智能体框架以解决多机器人操作的鲁棒性问题 manipulation large language model
10 Initiation Safety: A Missing Dimension in Generalist-Robot Safety 提出启动授权以解决通用机器人安全问题 humanoid VLA foundation model
11 Ace! Motion Planning of Professional-Level Table Tennis Serves with a Robot Arm 提出基于运动原语与优化的机器人乒乓球发球方法 model predictive control motion planning
12 WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time 提出WAM-TTT框架以解决机器人任务适应性问题 manipulation world action model world action models
13 GeoProp: Grounding Robot State in Vision for Generalist Manipulation 提出GeoProp以解决机器人状态与视觉对齐问题 manipulation diffusion policy ✅
14 PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation 提出PriGo框架以解决机器人操作中的泛化问题 manipulation imitation learning
15 Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing via Few-Shot Continual Adaptation 提出基于上下文感知的力估计方法以解决机器人表面擦拭中的接触力估计问题 manipulation
16 Dynamic Object Detection and Tracking in Construction: A Fisheye Camera and LiDAR Sensor Fusion Model 提出融合LiDAR与鱼眼相机的动态物体检测与跟踪模型 quadruped occupancy grid
17 SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization 提出SPECTRA框架以解决机器人技能泛化问题 manipulation imitation learning
18 Communicative Efficiency of Single vs. Multi-Axis Robot Neck Motion 提出信息论框架以优化机器人颈部运动的沟通效率 humanoid

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

#题目一句话要点标签🔗⭐
19 GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM 提出GeoGS-SLAM以解决稠密单目SLAM中的几何重建问题 visual SLAM 3DGS 3D reconstruction
20 Agent-Exploitation Affordances: From Basic to Complex Representation Patterns 提出合作性可供性以解决多智能体环境中的行动扩展问题 affordance
21 PLED-VINS: A Point-Line Event-Based Visual Inertial SLAM for Dynamic Environments 提出PLED-VINS以解决动态环境下视觉SLAM的挑战 visual SLAM

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

#题目一句话要点标签🔗⭐
22 Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders 提出多模态语音活动投影以解决社交机器人轮流发言预测问题 multimodal
23 Multi-Agent Robotic Control with Onboard Vision-Language Models 提出多智能体系统以解决机器人控制中的计算依赖问题 vision-language-action VLA
24 End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agent 提出FRAMe以解决人机协作飞行规划问题 large language model

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

#题目一句话要点标签🔗⭐
25 Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators 提出世界模型可接受性框架以增强机器人决策信任度 world model world models
26 Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation 提出Flow-ERD以解决交通模拟中的多样性与真实感问题 flow matching distillation ✅

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

#题目一句话要点标签🔗⭐
27 GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model 提出GemNav以解决视觉机器人导航中的数据效率问题 cross-embodiment large language model foundation model

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

#题目一句话要点标签🔗⭐
28 Learning Spatiotemporal Tubes for Full Class of Signal Temporal Logic Tasks for Control of Unknown Systems under Input Constraints 提出基于时空管道的控制框架以解决未知系统的STL任务 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页