cs.RO（2024-08-20）
📊 共 13 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱一：机器人控制 (Robot Control) (6 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (1)
🔬 支柱一：机器人控制 (Robot Control) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks | 提出IGANet，利用大模型先验知识解决指令引导的机器人操作可供性预测问题 | manipulation affordance large language model | ||
| 2 | Target-Oriented Object Grasping via Multimodal Human Guidance | 提出基于多模态人机引导的目标导向抓取网络，提升机器人抓取效率 | motion planning multimodal | ||
| 3 | RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands | 提出RP1M：一个大规模钢琴演奏运动数据集，用于双手动灵巧机器人 | manipulation bi-manual reinforcement learning | ||
| 4 | Towards reliable real-time trajectory optimization | 提出基于GPU加速的轨迹优化算法，提升机器人运动规划的可靠性和实时性 | trajectory optimization motion planning | ||
| 5 | OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Model | 提出OMEGA，通过状态空间模型实现动态环境中空地机器人的高效避障导航 | trajectory optimization Mamba state space model | ✅ | |
| 6 | MPGNet: Learning Move-Push-Grasping Synergy for Target-Oriented Grasping in Occluded Scenes | MPGNet：学习移动-推-抓取协同策略，解决遮挡场景下的目标导向抓取 | manipulation |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Bidirectional Intent Communication: A Role for Large Foundation Models | Bident：面向人机协作的、基于大模型的双向意图沟通框架 | foundation model multimodal | ||
| 8 | DVRP-MHSI: Dynamic Visualization Research Platform for Multimodal Human-Swarm Interaction | 提出DVRP-MHSI平台，加速多模态人-群交互研究，解决群体行为预测与控制难题。 | multimodal | ||
| 9 | All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents | 提出ARIO标准与数据集，用于训练通用多功能具身智能体 | embodied AI | ✅ | |
| 10 | A Mini-Review on Mobile Manipulators with Variable Autonomy | 综述可变自主移动操作机器人的研究现状、挑战与应用 | large language model | ||
| 11 | Where to Fetch: Extracting Visual Scene Representation from Large Pre-Trained Models for Robotic Goal Navigation | 提出基于视觉语言大模型的场景表征方法，提升机器人目标导航能力 | large language model | ||
| 12 | Kalib: Easy Hand-Eye Calibration with Reference Point Tracking | 提出Kalib以解决手眼标定中的繁琐设置问题 | foundation model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | Constrained Behavior Cloning for Robotic Learning | 提出几何与历史约束行为克隆(GHCBC)，提升机器人学习的鲁棒性和稳定性。 | imitation learning behavior cloning |