cs.RO（2024-09-26）

📊 共 25 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation 提出AV-ALOHA：结合主动视觉的双臂机器人模仿学习系统，提升复杂操作任务性能。 manipulation bi-manual teleoperation ✅
2 LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots LoopSR：一种用于足式机器人终身策略自适应的循环Sim-to-Real框架 legged robot legged locomotion locomotion
3 Target Pose Guided Whole-body Grasping Motion Generation for Digital Humans 提出一种目标姿态引导的数字人全身抓取动作生成框架 manipulation dexterous hand motion generation
4 RT-GuIDE: Real-Time Gaussian Splatting for Information-Driven Exploration 提出基于高斯溅射的实时信息驱动探索框架，用于机器人主动建图与导航。 motion planning gaussian splatting splatting ✅
5 Robust Ladder Climbing with a Quadrupedal Robot 提出基于强化学习的四足机器人攀爬梯子方案，提升工业巡检能力 quadruped legged robot reinforcement learning
6 GSON: A Group-based Social Navigation Framework with Large Multimodal Model GSON：基于大模型群组感知的社交导航框架，提升机器人社会适应性 motion planning multimodal
7 Canonical Representation and Force-Based Pretraining of 3D Tactile for Dexterous Visuo-Tactile Policy Learning 提出基于力感知的3D触觉表征与预训练方法，提升灵巧操作策略学习效果 manipulation dexterous hand dexterous manipulation
8 A Sim-to-Real Vision-based Lane Keeping System for a 1:10-scale Autonomous Vehicle 提出一种基于视觉的Sim2Real车道保持系统，用于1:10比例的自动驾驶车辆。 sim-to-real sim2real world model
9 Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction 提出RSRD以解决机器人模仿物体操作的问题 manipulation bi-manual
10 Model-Free versus Model-Based Reinforcement Learning for Fixed-Wing UAV Attitude Control Under Varying Wind Conditions 针对变风况下固定翼无人机姿态控制，提出优于PID和无模型RL的时序差分模型预测控制方法。 model predictive control reinforcement learning
11 Accelerated gradient descent for high frequency Model Predictive Control 针对高频模型预测控制，提出加速梯度下降方法以媲美二阶方法性能 model predictive control
12 Flat'n'Fold: A Diverse Multi-Modal Dataset for Garment Perception and Manipulation Flat'n'Fold：用于服装感知与操作的多模态数据集 manipulation ✅
13 SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation SKT：融合状态感知关键点轨迹与视觉-语言模型，用于机器人服装操作 manipulation
14 ReloPush: Multi-object Rearrangement in Confined Spaces with a Nonholonomic Mobile Robot Pusher ReloPush：非完整移动机器人推送器在受限空间内的多物体重排 manipulation traversability
15 Joint Localization and Planning using Diffusion 提出基于扩散模型的联合定位与规划方法，实现端到端机器人导航。 manipulation egocentric
16 SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning 提出SECURE，解决机器人交互式任务学习中对未知概念的处理问题 manipulation
17 Software for the SpaceDREAM Robotic Arm SpaceDREAM任务：用于在轨服务的阻抗控制机器人臂软件架构 manipulation

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

#题目一句话要点标签🔗⭐
18 HGS-Planner: Hierarchical Planning Framework for Active Scene Reconstruction Using 3D Gaussian Splatting HGS-Planner：基于3D高斯溅射的层级规划框架，用于主动场景重建 3D gaussian splatting 3DGS gaussian splatting
19 Traverse the Non-Traversable: Estimating Traversability for Wheeled Mobility on Vertically Challenging Terrain 提出TNT方法，利用车辆-地形交互数据驱动地估计轮式机器人于垂直复杂地形上的可通行性。 traversability
20 Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot 提出LEGS：一种可增量构建的、语言嵌入的高斯溅射方法，用于移动机器人构建房间尺度语义地图。 open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
21 VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain VertiSelector：基于自动课程学习的轮式机器人垂直地形移动方法 reinforcement learning curriculum learning
22 Cat-and-Mouse Satellite Dynamics: Divergent Adversarial Reinforcement Learning for Contested Multi-Agent Space Operations 提出Divergent Adversarial RL，解决复杂对抗环境下卫星自主规避问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
23 Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation Embodied-RAG：为具身智能体提出通用非参数具身记忆，用于检索和生成 multimodal
24 Learning to Drive via Asymmetric Self-Play 提出非对称自博弈方法，提升自动驾驶策略在长尾场景下的性能 zero-shot transfer

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

#题目一句话要点标签🔗⭐
25 Differentiable Contact Dynamics for Stable Object Placement Under Geometric Uncertainties 利用可微接触动力学，解决几何不确定性下的稳定物体放置问题 differentiable simulation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页