cs.RO（2024-08-12）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3)

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TacSL: A Library for Visuotactile Sensor Simulation and Learning	TacSL：用于视觉触觉传感器仿真与学习的库，加速触觉策略学习。	manipulation sim-to-real reinforcement learning	✅
2	UniT: Data Efficient Tactile Representation with Generalization to Unseen Objects	UniT：一种数据高效的触觉表征学习方法，可泛化到未知物体	manipulation policy learning representation learning	✅
3	Developing Smart MAVs for Autonomous Inspection in GPS-denied Constructions	提出一种用于GPS拒止环境自主巡检的智能MAV框架，实现高精度三维重建。	motion planning 3D gaussian splatting gaussian splatting
4	EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation	EyeSight Hand：集成视觉触觉传感器和柔顺驱动的灵巧机器人手	humanoid manipulation dexterous manipulation
5	Motion Planning for Minimally Actuated Serial Robots	针对最小驱动串联机器人，提出基于数据驱动逆运动学的MASR-RRT*运动规划算法。	motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs	提出RAHL框架，结合检索增强和分层强化学习，提升LLM在任务规划中的决策能力。	reinforcement learning HMR large language model
7	Body Transformer: Leveraging Robot Embodiment for Policy Learning	提出Body Transformer，利用机器人结构信息提升策略学习性能	reinforcement learning policy learning
8	Stable-BC: Controlling Covariate Shift with Stable Behavior Cloning	Stable-BC：通过稳定行为克隆控制协变量偏移，提升模仿学习鲁棒性	imitation learning behavior cloning

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

#	题目	一句话要点	标签	🔗	⭐
9	Generative Design of Multimodal Soft Pneumatic Actuators	提出基于高斯混合模型的软气动执行器生成设计方法，实现多模态驱动。	multimodal
10	Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications	Space-LLaVA：针对地外应用场景的视觉-语言模型	large language model foundation model instruction following
11	Text2Interaction: Establishing Safe and Preferable Human-Robot Interaction	Text2Interaction：利用大语言模型实现安全且符合用户偏好的人机交互	large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页