cs.RO（2024-12-11）

📊 共 16 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (4) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography SwarmGPT：结合大语言模型与安全运动规划的无人机群舞编排系统 motion planning large language model foundation model
2 Ask1: Development and Reinforcement Learning-Based Control of a Custom Quadruped Robot 设计并强化学习控制定制四足机器人Ask1，无需先验知识适应复杂地形 quadruped Unitree reinforcement learning
3 FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model FLIP：提出以光流为中心的生成式规划，作为通用操作任务的世界模型 manipulation world model representation learning ✅
4 TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning TidyBot++：用于机器人学习的开源全向移动操作平台 manipulation mobile manipulation teleoperation
5 Subspace-wise Hybrid RL for Articulated Object Manipulation 提出子空间混合强化学习(SwRL)框架，解决铰接物体操作中的复杂控制问题。 manipulation reinforcement learning
6 Bilevel Learning for Dual-Quadruped Collaborative Transportation under Kinematic and Anisotropic Velocity Constraints 提出双足四足机器人协同运输的分层学习方法，解决运动学和速度约束下的负载运输问题。 quadruped
7 Task-specific Self-body Controller Acquisition by Musculoskeletal Humanoids: Application to Pedal Control in Autonomous Driving 针对肌肉骨骼人形机器人，提出任务导向的自适应控制器，应用于自动驾驶踏板控制。 humanoid
8 Grasp Diffusion Network: Learning Grasp Generators from Partial Point Clouds with Diffusion Models in SO(3)xR3 提出Grasp Diffusion Network，利用扩散模型从单视角点云中生成抓取姿态 manipulation multimodal
9 DTAA: A Detect, Track and Avoid Architecture for navigation in spaces with Multiple Velocity Objects 提出DTAA架构，解决多运动目标场景下机器人安全导航问题 legged robot model predictive control
10 Grasping by parallel shape matching 提出基于并行形状匹配的抓取方法，提升机器人抓取的鲁棒性和效率 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
11 3DTTNet: Multimodal Fusion-Based 3D Traversable Terrain Modeling for Off-Road Environments 提出3DTTNet，通过多模态融合进行越野环境下的3D可通行地形建模。 occupancy grid traversability multimodal
12 Drift-free Visual SLAM using Digital Twins 提出基于数字孪生的无漂移视觉SLAM，提升城市环境定位精度 visual SLAM VIO feature matching
13 DOGE: An Extrinsic Orientation and Gyroscope Bias Estimation for Visual-Inertial Odometry Initialization 提出DOGE，用于视觉惯性里程计初始化时外参旋转和陀螺仪偏差的精确估计。 VIO
14 THUD++: Large-Scale Dynamic Indoor Scene Dataset and Benchmark for Mobile Robots THUD++：用于移动机器人的大规模动态室内场景数据集与基准 scene understanding

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

#题目一句话要点标签🔗⭐
15 Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation 提出Multi-GraspLLM以解决多手语义引导抓取生成问题 large language model multimodal
16 Intelligent Control of Robotic X-ray Devices using a Language-promptable Digital Twin 提出基于语言提示的数字孪生方法，实现机器人X射线设备的智能控制 foundation model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页