cs.RO（2025-04-30）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Pre-trained Large Language Models with Refined Prompting for Online Task and Motion Planning LLM-PAS：利用预训练大语言模型与优化Prompt实现在线任务与运动规划 motion planning large language model task and motion planning
2 Whleaper: A 10-DOF Flexible Bipedal Wheeled Robot Whleaper：一种具有10自由度的高柔性双足轮式机器人，提升复杂地形适应性。 legged robot humanoid bipedal
3 Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning 提出基于概率模型的强化学习方法GC-PMPC，解决灵巧手多目标操作任务。 manipulation dexterous hand MPC
4 LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning 提出LangWBC，通过端到端学习实现语言引导的人形机器人全身控制 humanoid humanoid robot whole-body control
5 LLM-based Interactive Imitation Learning for Robotic Manipulation 提出LLM-iTeach框架，利用大语言模型作为交互式教师提升机器人操作模仿学习性能。 manipulation imitation learning behavior cloning ✅
6 One Net to Rule Them All: Domain Randomization in Quadcopter Racing Across Different Platforms 提出基于领域随机化的四旋翼通用控制网络，实现跨平台无人机竞速。 sim-to-real domain randomization
7 RoboGround: Robotic Manipulation with Grounded Vision-Language Priors RoboGround：利用视觉-语言先验知识进行机器人操作，提升泛化能力 manipulation
8 Provably-Safe, Online System Identification 提出一种在线安全系统辨识框架，用于精确操作任务中未知负载的惯性参数辨识。 manipulation ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
9 Investigating Adaptive Tuning of Assistive Exoskeletons Using Offline Reinforcement Learning: Challenges and Insights 利用离线强化学习自适应调节辅助外骨骼：挑战与启示 reinforcement learning offline reinforcement learning
10 Deep Reinforcement Learning Policies for Underactuated Satellite Attitude Control 提出基于深度强化学习的卫星姿态控制策略，解决欠驱动场景下的再定向问题 reinforcement learning deep reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
11 Path Planning on Multi-level Point Cloud with a Weighted Traversability Graph 提出一种基于加权可通行性图的多层点云路径规划方法，适用于复杂地形 traversability
12 LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics 提出LLM驱动的具身智能体，用于家庭机器人中记忆增强的任务规划 scene understanding ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
13 UAV-VLN: End-to-End Vision Language guided Navigation for UAVs 提出UAV-VLN，用于无人机在复杂环境中基于自然语言指令的端到端视觉语言导航。 spatial relationship VLN large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页