cs.RO（2025-02-26）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models 提出基于分层视觉-语言-动作模型的开放式指令跟随机器人系统 dual-arm vision-language-action instruction following
2 ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration ObjectVLA：无需演示的端到端开放世界物体操作 manipulation dexterous manipulation policy learning
3 Think on your feet: Seamless Transition between Human-like Locomotion in Response to Changing Commands 提出基于模仿学习的人形机器人运动控制方法，实现复杂指令下的流畅运动过渡 humanoid humanoid robot locomotion
4 Stability Analysis of Deep Reinforcement Learning for Multi-Agent Inspection in a Terrestrial Testbed 提出一种分层深度强化学习框架，用于多智能体卫星自主巡检任务，并在地面测试平台上验证其稳定性。 sim-to-real reinforcement learning deep reinforcement learning
5 Hybrid Robot Learning for Automatic Robot Motion Planning in Manufacturing 提出一种混合强化学习的机器人运动规划方法，用于自动化制造场景。 motion planning reinforcement learning deep reinforcement learning
6 Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments 提出GVNav，解决低视角机器人视觉语言导航中的泛化性问题 quadruped spatiotemporal VLN
7 Attention-Guided Integration of CLIP and SAM for Precise Object Masking in Robotic Manipulation 提出基于注意力引导的CLIP和SAM集成方法，提升机器人操作中物体掩膜精度 manipulation multimodal
8 RL-OGM-Parking: Lidar OGM-Based Hybrid Reinforcement Learning Planner for Autonomous Parking 提出基于激光雷达OGM和混合强化学习的自动泊车规划器 sim-to-real reinforcement learning occupancy grid
9 Surface-Based Manipulation with Modular Foldable Robots 提出基于表面的模块化折叠机器人操作方法，解决复杂物体操作难题 manipulation
10 CPG-Based Manipulation with Multi-Module Origami Robot Surface 提出基于CPG的多模块折纸机器人表面操作方法，适用于不同尺寸和刚度的物体 manipulation
11 Leg Exoskeleton Odometry using a Limited FOV Depth Sensor 针对腿部外骨骼，提出一种基于有限FOV深度传感器的里程计算法 legged robot elevation map
12 Image-Based Roadmaps for Vision-Only Planning and Control of Robotic Manipulators 提出基于图像的机器人操作臂运动规划方法，无需显式模型和关节编码器 motion planning
13 Diffusion-based Planning with Learned Viability Filters 提出基于扩散模型的学习型可行性过滤器，用于约束运动规划并提升复杂3D运动任务性能。 locomotion

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

#题目一句话要点标签🔗⭐
14 Increasing the Task Flexibility of Heavy-Duty Manipulators Using Visual 6D Pose Estimation of Objects 提出基于视觉6D位姿估计的重型机械臂工具定位方法，提升任务灵活性。 visual SLAM 6D pose estimation
15 BEV-LIO(LC): BEV Image Assisted LiDAR-Inertial Odometry with Loop Closure BEV图像辅助的LiDAR惯性里程计，通过闭环检测提升定位精度 LIO ✅
16 SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images DarkSLAM：一种自监督学习的单目热成像SLAM系统，用于弱光环境下的位姿、深度和回环检测。 visual odometry visual SLAM depth estimation
17 QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries QueryAdapter：通过自然语言查询快速自适应视觉-语言模型，提升机器人环境感知能力。 affordance Ego4D

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

#题目一句话要点标签🔗⭐
18 LiDAR Registration with Visual Foundation Models 利用视觉基础模型DINOv2特征，实现鲁棒的LiDAR点云配准 foundation model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Clouds MaskPlanner：一种基于学习的、以物体为中心的3D点云运动生成方法 motion generation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页