cs.RO（2024-05-24）

📊 共 10 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (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) (4 篇)

#题目一句话要点标签🔗⭐
1 Dynamic Planning for Sequential Whole-body Mobile Manipulation 提出基于虚拟运动链的动态序列式移动操作规划框架，解决动态环境中移动操作机器人的长期任务规划和实时运动生成问题。 manipulation mobile manipulation MPC
2 Automated Assessment and Adaptive Multimodal Formative Feedback Improves Psychomotor Skills Training Outcomes in Quadrotor Teleoperation 提出基于时序逻辑和多模态自适应反馈的四旋翼遥操作技能训练系统 teleoperation multimodal
3 TD3 Based Collision Free Motion Planning for Robot Navigation 提出基于TD3-DWA的机器人导航方法，解决复杂环境下的避障运动规划问题 motion planning reinforcement learning deep reinforcement learning
4 MeMo: Meaningful, Modular Controllers via Noise Injection MeMo：通过噪声注入学习有意义的模块化机器人控制器，实现快速迁移 locomotion behavior cloning

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

#题目一句话要点标签🔗⭐
5 Neural Elevation Models for Terrain Mapping and Path Planning 提出神经高程模型NEMos，用于从图像生成地形地图并进行路径规划。 NeRF neural radiance field
6 GroundGrid:LiDAR Point Cloud Ground Segmentation and Terrain Estimation GroundGrid：基于2D高程图的激光雷达点云地面分割与地形估计 elevation map ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
7 SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction SMART：基于Next-token预测的可扩展多智能体实时运动生成 motion generation ✅

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

#题目一句话要点标签🔗⭐
8 A Systematic Review on Custom Data Gloves 系统性回顾定制数据手套，为标准化奠定基础 human motion

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

#题目一句话要点标签🔗⭐
9 Conditional Variational Auto Encoder Based Dynamic Motion for Multi-task Imitation Learning 提出基于条件变分自编码器和动态运动原语的多任务模仿学习框架 imitation learning

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

#题目一句话要点标签🔗⭐
10 LLM-based Robot Task Planning with Exceptional Handling for General Purpose Service Robots 提出基于约束LLM提示和异常处理的机器人任务规划方法 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页