cs.RO（2024-05-23）
📊 共 14 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱一：机器人控制 (Robot Control) (5)
支柱三：空间感知与语义 (Perception & Semantics) (4)
支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (2)
🔬 支柱一：机器人控制 (Robot Control) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A Unification Between Deep-Learning Vision, Compartmental Dynamical Thermodynamics, and Robotic Manipulation for a Circular Economy | 融合深度学习视觉、热力学和机器人操作，为循环经济构建统一框架 | manipulation reinforcement learning | ||
| 2 | Visuo-Tactile Keypoint Correspondences for Object Manipulation | 提出基于视觉-触觉关键点对应关系的物体操作方法，实现精准操作。 | manipulation | ||
| 3 | Evolution and learning in differentiable robots | 提出基于可微仿真的进化学习框架，实现机器人形态与控制策略的协同优化。 | sim2real differentiable simulation | ||
| 4 | ReachBot Field Tests in a Mojave Desert Lava Tube as a Martian Analog | ReachBot：一种用于火星模拟环境熔岩管探测的可伸缩臂机器人 | locomotion | ||
| 5 | Optimal Whole Body Trajectory Planning for Mobile Manipulators in Planetary Exploration and Construction | 提出Optimal Whole Body Planner以解决移动操控器轨迹规划问题 | motion planning |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Advancements in Translation Accuracy for Stereo Visual-Inertial Initialization | 提出基于3自由度BA的视觉惯性初始化方法，提升平移精度。 | visual odometry visual SLAM | ||
| 7 | CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World Environments | CoPeD：提出真实场景下多机器人协同感知数据集，促进高层场景理解研究 | scene understanding | ||
| 8 | Efficient Robot Learning for Perception and Mapping | 研究高效机器人学习方法，降低感知与建图对人工标注的依赖 | scene understanding | ||
| 9 | VINS-Multi: A Robust Asynchronous Multi-camera-IMU State Estimator | 提出VINS-Multi，解决异步多相机-IMU系统的鲁棒状态估计问题。 | VIO |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | A Survey on Vision-Language-Action Models for Embodied AI | 对具身智能中视觉-语言-动作模型（VLA）的全面综述 | embodied AI vision-language-action VLA | ✅ | |
| 11 | Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction | 提出BMCLOP框架，提升人机交互中多模态意图识别的置信度和准确率 | multimodal | ||
| 12 | Skip-SCAR: Hardware-Friendly High-Quality Embodied Visual Navigation | Skip-SCAR：面向硬件友好的高质量具身视觉导航框架 | embodied AI |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | Agentic Skill Discovery | 提出Agentic Skill Discovery框架，利用LLM自主发现机器人技能 | reinforcement learning large language model language conditioned | ||
| 14 | Transformers for Image-Goal Navigation | 提出基于Transformer的图像目标导航模型，解决长时程导航问题 | reinforcement learning scene understanding |