cs.RO（2025-05-30）

📊 共 20 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#题目一句话要点标签🔗⭐
1 Humanoid Loco-Manipulations Pattern Generation and Stabilization Control 提出一种人型机器人行走操作控制策略，解决复杂外力干扰下的平衡问题。 humanoid humanoid robot bipedal
2 DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation DexMachina：用于灵巧双手动灵巧操作的功能重定向 manipulation dexterous hand dexterous manipulation
3 SignBot: Learning Human-to-Humanoid Sign Language Interaction SignBot：学习人与人形机器人之间手语交互的框架 humanoid humanoid robot humanoid control
4 Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey 综述：交互式模仿学习在灵巧机器人操作中的挑战与展望 humanoid humanoid robot manipulation
5 Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control 提出SoFTA框架，解决人形机器人运动中末端执行器稳定控制难题 humanoid humanoid locomotion locomotion
6 MagicGripper: A Multimodal Sensor-Integrated Gripper for Contact-Rich Robotic Manipulation MagicGripper：用于接触式机器人操作的多模态传感器集成夹爪 manipulation multimodal
7 Learning Aerodynamics for the Control of Flying Humanoid Robots 针对飞行人形机器人，提出基于学习的空气动力学建模与控制方法 humanoid humanoid robot locomotion
8 Bi-Manual Joint Camera Calibration and Scene Representation 提出Bi-JCR框架，解决双臂机器人联合相机标定与场景重建问题。 manipulation bi-manual bimanual manipulation
9 Reactive Aerobatic Flight via Reinforcement Learning 提出基于强化学习的四旋翼飞行器敏捷飞行控制框架，实现反应式特技飞行。 sim-to-real domain randomization trajectory optimization
10 Navigation of a Three-Link Microswimmer via Deep Reinforcement Learning 提出基于深度强化学习的三连杆微型游泳器导航方法，实现复杂环境下的自主运动。 motion planning reinforcement learning deep reinforcement learning
11 Imitation Learning-Based Path Generation for the Complex Assembly of Deformable Objects 提出基于模仿学习的路径生成方法，简化柔性物体复杂装配的运动规划。 motion planning imitation learning behavior cloning
12 Safety-Aware Robust Model Predictive Control for Robotic Arms in Dynamic Environments 提出安全感知鲁棒模型预测控制，解决动态环境中机械臂的避障问题 MPC model predictive control
13 Lazy Heuristic Search for Solving POMDPs with Expensive-to-Compute Belief Transitions 提出Lazy RTDP-Bel和Lazy LAO*，通过延迟计算降低POMDP中高代价信念状态转移的规划时间。 manipulation
14 EL-AGHF: Extended Lagrangian Affine Geometric Heat Flow 提出扩展拉格朗日仿射几何热流方法，解决非完整系统运动规划中的动态间隙问题。 motion planning
15 SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping SR3D：释放单视角3D重建能力，助力透明和镜面物体抓取 manipulation
16 Towards Tangible Immersion for Cobot Programming-by-Demonstration: Visual, Tactile and Haptic Interfaces for Mixed-Reality Cobot Automation in Semiconductor Manufacturing 提出一种基于抽象操作原语的机器人反应式操作建模方法，实现知识在不同机器人间的迁移。 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
17 Understanding while Exploring: Semantics-driven Active Mapping 提出ActiveSGM，通过语义驱动的主动探索实现高效语义地图构建 3D gaussian splatting 3DGS gaussian splatting
18 Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments 提出Hi-Dyna Graph，用于人机交互环境中机器人自主导航的动态场景图构建。 NeRF affordance human-object interaction

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

#题目一句话要点标签🔗⭐
19 RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward RoboMoRe：基于LLM的机器人协同设计，联合优化形态与奖励函数 reward shaping large language model

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

#题目一句话要点标签🔗⭐
20 Curate, Connect, Inquire: A System for Findable Accessible Interoperable and Reusable (FAIR) Human-Robot Centered Datasets 提出一种FAIR原则的人机交互数据集管理系统，提升数据可访问性和可理解性。 embodied AI

⬅️ 返回 cs.RO 首页 · 🏠 返回主页