cs.RO（2024-10-16）

📊 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) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions Harmon：基于语言描述生成人形机器人全身运动 humanoid humanoid robot motion generation ✅
2 Differentiable Motion Manifold Primitives for Reactive Motion Generation under Kinodynamic Constraints 提出可微运动流形基元(DMMP)，用于满足运动学约束的反应式运动生成 trajectory optimization motion generation reactive motion
3 Hybrid Decision Making for Scalable Multi-Agent Navigation: Integrating Semantic Maps, Discrete Coordination, and Model Predictive Control 提出一种混合决策框架，用于可扩展的多智能体导航，集成了语义地图、离散协调和模型预测控制。 model predictive control semantic map
4 Characterizing and Optimizing Real-Time Optimal Control for Embedded SoCs 针对嵌入式SoC，探索并优化实时最优控制算法的硬件架构 locomotion manipulation MPC
5 A Data-driven Contact Estimation Method for Wheeled-Biped Robots 针对轮式双足机器人，提出一种数据驱动的接触估计方法 biped
6 Physics-Informed Learning for the Friction Modeling of High-Ratio Harmonic Drives 提出基于物理信息神经网络的谐波驱动摩擦力建模方法，提升机器人控制性能。 humanoid humanoid robot
7 Faster Algorithms for Growing Collision-Free Convex Polytopes in Robot Configuration Space 提出IRIS-NP2和IRIS-ZO算法，加速机器人构型空间中无碰撞凸多胞形的构建。 trajectory optimization motion planning
8 AdaCropFollow: Self-Supervised Online Adaptation for Visual Under-Canopy Navigation AdaCropFollow：面向作物下自主导航的自监督在线语义关键点自适应方法 manipulation
9 Learning Differentiable Tensegrity Dynamics using Graph Neural Networks 提出基于图神经网络的可微张拉整体动力学学习方法，提升仿真精度与效率。 locomotion ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
10 Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features Flex：基于预训练视觉语言模型特征的端到端文本指令视觉导航 behavior cloning foundation model
11 Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving RAPID：融合LLM数据合成与策略自适应的鲁棒自动驾驶强化学习方法 reinforcement learning distillation large language model
12 Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners 提出基于信息论目标最大化的强化学习方法，提升机器人对未知人群行为的泛化能力 reinforcement learning
13 Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration 提出一种任务驱动探索的强化学习算法，提升线性时序逻辑目标下的样本效率。 reinforcement learning

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

#题目一句话要点标签🔗⭐
14 3D Gaussian Splatting in Robotics: A Survey 综述：3D高斯溅射在机器人领域的应用与进展 3D gaussian splatting 3DGS gaussian splatting
15 BlabberSeg: Real-Time Embedded Open-Vocabulary Aerial Segmentation BlabberSeg：用于无人机实时嵌入式开放词汇空中分割 open-vocabulary open vocabulary
16 Towards Autonomous Indoor Parking: A Globally Consistent Semantic SLAM System and A Semantic Localization Subsystem 提出全局一致语义SLAM系统，实现复杂室内停车场自主泊车 semantic mapping semantic map

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
17 Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentation 提出一种可配置的具身数据生成方法，用于提升机器人平台上的类别无关RGB-D视频分割性能。 foundation model
18 In-Context Learning Enables Robot Action Prediction in LLMs RoboPrompt：利用上下文学习使LLM直接预测机器人动作 large language model ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 The State of Robot Motion Generation 机器人运动生成方法综述：回顾50年研究进展并展望未来集成方向 motion generation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页