cs.RO（2024-07-10）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark BiGym：一个面向移动双臂操作的、基于演示学习的基准测试环境 manipulation bi-manual reinforcement learning
2 Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation 提出一种约束灵巧操作学习系统，用于蔬菜削皮任务 manipulation dexterous manipulation ✅
3 Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems 利用视觉-语言导航系统表征漏洞进行恶意路径篡改 manipulation VLN large language model
4 Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation 基于绿幕增强的机器人操作场景泛化方法 manipulation reinforcement learning imitation learning
5 Continuous Control with Coarse-to-fine Reinforcement Learning 提出粗到精强化学习框架，解决连续动作空间中样本效率低的挑战 manipulation reinforcement learning behavior cloning
6 AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation AdaptiGraph：用于机器人操作的材料自适应图神经网络动力学模型 manipulation predictive model ✅
7 Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing 提出基于触觉皮肤的强化学习方法，实现灵巧的物体手中平移 manipulation dexterous manipulation sim-to-real ✅
8 Imitation Learning with Additional Constraints on Motion Style using Parametric Bias 提出基于参数化偏置的模仿学习方法，实现运动风格约束下的机器人动作复现。 humanoid imitation learning
9 Estimation and Control of Motor Core Temperature with Online Learning of Thermal Model Parameters: Application to Musculoskeletal Humanoids 提出一种基于在线学习热模型参数的电机温度估计与控制方法，应用于肌肉骨骼人形机器人。 humanoid
10 AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries AutoMate：面向多样几何体的专家和通用机器人组装策略学习框架 sim-to-real policy learning character animation ✅
11 FLAIR: Feeding via Long-horizon AcquIsition of Realistic dishes FLAIR：利用长时程学习获取真实餐食，实现个性化机器人喂食 manipulation foundation model
12 RoCap: A Robotic Data Collection Pipeline for the Pose Estimation of Appearance-Changing Objects 提出Rocap机器人数据收集流程，用于外观变化物体的姿态估计 manipulation
13 Adaptive Robotic Tool-Tip Control Learning Considering Online Changes in Grasping State 提出一种自适应机器人末端控制学习方法，解决抓取状态在线变化问题 manipulation
14 Object Recognition, Dynamic Contact Simulation, Detection, and Control of the Flexible Musculoskeletal Hand Using a Recurrent Neural Network with Parametric Bias 提出基于参数偏置循环神经网络的柔性肌骨手控制方法，实现对象识别、接触模拟与控制。 humanoid

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

#题目一句话要点标签🔗⭐
15 Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs 提出 Mobility VLA，结合长文本 VLM 和拓扑图解决多模态指令导航问题 vision-language-action VLA multimodal

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

#题目一句话要点标签🔗⭐
16 Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach 提出基于扩散模型的任务特定策略生成方法，提升机器人行为基础模型的可解释性。 reinforcement learning foundation model

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

#题目一句话要点标签🔗⭐
17 MoVEInt: Mixture of Variational Experts for Learning Human-Robot Interactions from Demonstrations MoVEInt：基于变分专家混合模型的演示学习人机交互 human-to-robot multimodal

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

#题目一句话要点标签🔗⭐
18 MSC-LIO: An MSCKF-Based LiDAR-Inertial Odometry with Same-Plane Cluster Tracking 提出基于MSCKF的激光雷达惯性里程计MSC-LIO，通过同平面聚类跟踪提升效率。 LIO

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
19 Missile detection and destruction robot using detection algorithm 提出一种基于多传感器融合的低成本导弹探测与摧毁机器人方案 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页