cs.RO（2024-10-24）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 Data Scaling Laws in Imitation Learning for Robotic Manipulation 研究模仿学习中机器人操作的数据缩放规律，实现零样本泛化 manipulation imitation learning
2 Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling 提出基于动态3D高斯追踪的图神经网络动力学建模方法，用于机器人交互视频中的物体运动预测。 manipulation 3D gaussian splatting 3DGS
3 Self-Improving Autonomous Underwater Manipulation AquaBot：提出一种自提升的水下自主操作机器人系统，超越人类遥操作性能。 manipulation teleoperation behavior cloning
4 SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment SkillMimicGen：自动化生成演示数据，提升机器人技能学习与部署效率 manipulation sim-to-real motion planning
5 Embodied Manipulation with Past and Future Morphologies through an Open Parametric Hand Design 提出一种开放参数化手部设计，用于探索具身操作和形态学对操作的影响。 manipulation dexterous manipulation
6 Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning 提出一种基于强化学习的多无人机编队控制方法，用于静态和动态避障。 sim-to-real reinforcement learning curriculum learning
7 UGotMe: An Embodied System for Affective Human-Robot Interaction UGotMe：面向多人对话的情感人机交互具身系统，解决噪声和实时性问题 humanoid humanoid robot multimodal ✅
8 Swarm manipulation: An efficient and accurate technique for multi-object manipulation in virtual reality 提出基于群体控制的VR多对象交互方法，提升虚拟环境中的操作效率和用户体验 manipulation
9 Breaking Down the Barriers: Investigating Non-Expert User Experiences in Robotic Teleoperation in UK and Japan TELESIM框架结合VR控制，提升非专家用户远程操控机器人手臂的体验与信任度 teleoperation
10 ANAVI: Audio Noise Awareness using Visuals of Indoor environments for NAVIgation 提出ANAVI，利用室内视觉信息实现机器人音频噪声感知与路径规划 Unitree PULSE
11 SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstration SSFold：利用人类演示中的图动力学学习折叠任意褶皱的布料 manipulation sim-to-real ✅
12 Versatile Demonstration Interface: Toward More Flexible Robot Demonstration Collection 提出多功能示教界面VDI，简化机器人示教数据采集，适用于工业场景。 teleoperation
13 Learning to Look: Seeking Information for Decision Making via Policy Factorization 提出DISaM，通过策略分解解决机器人操作任务中的信息搜寻问题 manipulation
14 A generic approach for reactive stateful mitigation of application failures in distributed robotics systems deployed with Kubernetes 提出基于行为树的通用方法，用于Kubernetes部署的分布式机器人系统故障反应式状态缓解。 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
15 Zero-shot Object Navigation with Vision-Language Models Reasoning 提出VLTNet，利用视觉语言模型和思维树网络实现零样本物体导航 semantic mapping semantic map
16 Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images 提出TCNet，一种任务自适应的红外热成像色调映射网络，提升多种任务性能。 depth estimation monocular depth ✅
17 Search-Based Path Planning in Interactive Environments among Movable Obstacles 提出PAMO*算法，解决交互环境中可移动障碍物间的搜索式路径规划问题 occupancy grid

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

#题目一句话要点标签🔗⭐
18 Reinforcement Learning Controllers for Soft Robots using Learned Environments 提出基于学习环境的强化学习控制器，用于软体机器人控制。 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
19 Creating and Repairing Robot Programs in Open-World Domains RoboRepair：利用LLM生成机器人程序并进行错误恢复，提升开放世界任务的鲁棒性 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页