cs.RO（2026-01-21）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 TacUMI: A Multi-Modal Universal Manipulation Interface for Contact-Rich Tasks TacUMI：用于接触丰富任务的多模态通用操作界面 manipulation
2 Learning a Unified Latent Space for Cross-Embodiment Robot Control 提出一种统一的跨具身人形机器人控制学习框架 humanoid humanoid robot dual-arm
3 HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation HumanoidVLM：基于视觉-语言引导的阻抗控制，用于人型机器人富接触操作 humanoid humanoid robot manipulation
4 Spatially Generalizable Mobile Manipulation via Adaptive Experience Selection and Dynamic Imagination 提出自适应经验选择与动态想象，提升移动操作的空间泛化能力 manipulation mobile manipulation
5 Vision-Language Models on the Edge for Real-Time Robotic Perception 边缘计算赋能人形机器人：实时视觉-语言模型部署与性能优化 humanoid humanoid robot Unitree
6 UniCon: A Unified System for Efficient Robot Learning Transfers UniCon：一种用于高效机器人学习迁移的统一系统 sim-to-real UniCon
7 Explainable OOHRI: Communicating Robot Capabilities and Limitations as Augmented Reality Affordances 提出X-OOHRI，通过AR界面提升人机交互中机器人能力的可解释性。 manipulation affordance
8 V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks V-CAGE：上下文感知生成与验证，用于可扩展的长时程具身任务 manipulation penetration geometric consistency
9 Graph-Based Adaptive Planning for Coordinated Dual-Arm Robotic Disassembly of Electronic Devices (eGRAP) 提出基于图的自适应规划方法以实现电子设备的双臂机器人拆解 dual-arm
10 CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes CADGrasp：学习杂乱场景中通用灵巧抓取的接触与碰撞感知方法 dexterous hand
11 Risk Estimation for Automated Driving 提出一种通用的、计算高效的风险评估方法，用于提升自动驾驶安全性。 motion planning

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

#题目一句话要点标签🔗⭐
12 TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control TIDAL：时序交错扩散与动作循环，实现高频VLA控制 vision-language-action VLA
13 A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control 提出NeuroVLA，一种脑启发的具身智能框架，用于快速灵敏的机器人控制 vision-language-action VLA
14 Probing Prompt Design for Socially Compliant Robot Navigation with Vision Language Models 针对社交机器人导航，提出基于认知理论的提示工程方法，提升小VLM的社交合规性。 large language model

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

#题目一句话要点标签🔗⭐
15 FARE: Fast-Slow Agentic Robotic Exploration FARE：一种基于快慢Agent的机器人自主探索框架 reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
16 ExPrIS: Knowledge-Level Expectations as Priors for Object Interpretation from Sensor Data ExPrIS：利用知识先验提升机器人传感器数据中的物体理解 scene understanding

⬅️ 返回 cs.RO 首页 · 🏠 返回主页