cs.RO（2026-01-26）

📊 共 12 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 A Pragmatic VLA Foundation Model LingBot-VLA：基于大规模真实世界数据的实用型视觉-语言-动作机器人基础模型 manipulation dual-arm vision-language-action
2 ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection ExoGS：一种可扩展操作数据收集的4D实-仿-实框架 manipulation sim-to-real teleoperation ✅
3 Trustworthy Evaluation of Robotic Manipulation: A New Benchmark and AutoEval Methods 提出Eval-Actions基准和AutoEval架构，实现机器人操作行为的可信评估。 manipulation teleoperation imitation learning ✅
4 Quest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation Quest2ROS2：用于双臂VR遥操作的ROS2开源框架，扩展机器人数据采集 bi-manual teleoperation VR teleoperation ✅
5 Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge 提出MARS挑战赛，探索多智能体机器人系统中基于视觉-语言模型的规划与控制问题。 manipulation embodied AI large language model
6 Fast and Safe Trajectory Optimization for Mobile Manipulators With Neural Configuration Space Distance Field 提出基于神经配置空间距离场的移动机械臂快速安全轨迹优化方法 manipulation mobile manipulation trajectory optimization
7 Grasp-and-Lift: Executable 3D Hand-Object Interaction Reconstruction via Physics-in-the-Loop Optimization 提出基于物理引擎优化的抓取与抬起动作重建方法，提升交互真实性 manipulation dexterous hand policy learning
8 Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation 提出基于注意力机制的神经增强卡尔曼滤波器，用于腿足机器人状态估计，解决滑移误差问题。 legged robot

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
9 DV-VLN: Dual Verification for Reliable LLM-Based Vision-and-Language Navigation 提出DV-VLN以解决LLM驱动的视觉语言导航中的决策不可靠问题 VLN large language model chain-of-thought ✅
10 SG-CADVLM: A Context-Aware Decoding Powered Vision Language Model for Safety-Critical Scenario Generation 提出SG-CADVLM，利用上下文感知解码生成安全关键场景，提升自动驾驶验证效率。 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🔗⭐
11 TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion 提出工具中心逆动力学模型(TC-IDM)，用于生成式世界模型驱动的零样本机器人运动控制。 world model embodied AI vision-language-action
12 Goal-oriented Communication for Fast and Robust Robotic Fault Detection and Recovery 提出面向目标的通信框架，加速并增强机器人故障检测与恢复 distillation spatial relationship large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页