cs.RO（2025-03-08）

📊 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) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#题目一句话要点标签🔗⭐
1 ReJSHand: Efficient Real-Time Hand Pose Estimation and Mesh Reconstruction Using Refined Joint and Skeleton Features ReJSHand：利用精细化关节与骨骼特征实现高效实时手部姿态估计与网格重建 manipulation dexterous manipulation motion tracking ✅
2 Deep Reinforcement Learning-Based Semi-Autonomous Control for Magnetic Micro-robot Navigation with Immersive Manipulation 提出基于深度强化学习的半自主控制框架，用于磁微型机器人在沉浸式操作下的导航。 manipulation reinforcement learning deep reinforcement learning
3 T-CBF: Traversability-based Control Barrier Function to Navigate Vertically Challenging Terrain 提出基于可通行性的控制屏障函数，用于垂直复杂地形的机器人安全导航 motion planning traversability
4 FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matching FlowMP：利用条件流匹配学习运动场，提升机器人运动规划性能 motion planning flow matching
5 Efficient Gradient-Based Inference for Manipulation Planning in Contact Factor Graphs 提出基于梯度的高效推理方法，用于接触因子图中的操作规划 manipulation
6 FSDP: Fast and Safe Data-Driven Overtaking Trajectory Planning for Head-to-Head Autonomous Racing Competitions 提出FSDP，用于资源受限的自主竞速中快速安全的数据驱动超车轨迹规划。 model predictive control ✅

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

#题目一句话要点标签🔗⭐
7 HIPPO-MAT: Decentralized Task Allocation Using GraphSAGE and Multi-Agent Deep Reinforcement Learning HIPPO-MAT：基于图神经网络和多智能体深度强化学习的去中心化任务分配框架 reinforcement learning deep reinforcement learning
8 FloPE: Flower Pose Estimation for Precision Pollination FloPE：面向精准授粉的花朵姿态估计框架，适用于计算受限的机器人系统 distillation 3D gaussian splatting gaussian splatting
9 On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning 提出基于强化学习的自适应行为树策略，解决机器人动态环境下的任务变异问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
10 STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems STAR框架：利用基础模型和知识图谱实现机器人任务规划与故障恢复 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
11 GAT-Grasp: Gesture-Driven Affordance Transfer for Task-Aware Robotic Grasping GAT-Grasp：手势驱动的灵巧抓取，实现任务感知机器人操作 affordance human-object interaction

⬅️ 返回 cs.RO 首页 · 🏠 返回主页