cs.RO（2025-05-20）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 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 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic Manipulation DORA：面向灵巧操作的物体可供性引导强化学习 manipulation reinforcement learning affordance
2 Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning SPI-Active：结合主动探索的采样系统辨识，提升腿足机器人Sim2Real迁移性能 legged robot locomotion sim-to-real
3 Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning 提出TR-DRL框架，利用时间反演对称性提升机器人操作深度强化学习的样本效率。 manipulation reinforcement learning deep reinforcement learning
4 Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams 提出基于分层多智能体强化学习的四足机器人足球框架，实现自主协同与对抗。 quadruped legged robot legged locomotion
5 AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory AutoBio：用于数字生物实验室机器人自动化的模拟与基准测试平台 manipulation vision-language-action VLA
6 Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning 提出SMS框架，结合3D高斯溅射、视觉基础模型和物理仿真，实现通用物理常识机器人规划 manipulation 3D gaussian splatting gaussian splatting
7 Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation 提出基于预测力注意力的自适应视觉-触觉融合方法，用于灵巧操作 manipulation dexterous manipulation ✅
8 Semantically-driven Deep Reinforcement Learning for Inspection Path Planning 提出一种语义驱动的深度强化学习方法，用于未知环境下的自主检查路径规划。 sim2real reinforcement learning deep reinforcement learning
9 Sketch Interface for Teleoperation of Mobile Manipulator to Enable Intuitive and Intended Operation: A Proof of Concept 提出基于草图的移动机械臂遥操作界面，实现直观和意图驱动的操作 manipulation mobile manipulation teleoperation
10 Certifiably Safe Manipulation of Deformable Linear Objects via Joint Shape and Tension Prediction 提出基于形状与张力联合预测的可认证安全柔性线性物体操作方法 manipulation motion planning predictive model
11 Robust Immersive Bilateral Teleoperation of Beyond-Human-Scale Systems with Enhanced Transparency and Sense of Embodiment 提出一种增强透明度和临场感的超人尺度系统鲁棒沉浸式双边遥操作框架 teleoperation motion tracking
12 RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation RoboRAN：用于强化学习自主导航的统一机器人框架，支持多平台部署。 sim-to-real reinforcement learning
13 Duawlfin: A Drone with Unified Actuation for Wheeled Locomotion and Flight Operation Duawlfin：一种采用统一驱动方式，实现轮式运动和飞行操作的无人机 locomotion
14 MultiDrive: A Co-Simulation Framework Bridging 2D and 3D Driving Simulation for AV Software Validation MultiDrive：桥接2D和3D驾驶仿真的AV软件验证协同仿真框架 sim-to-real motion planning ✅

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

#题目一句话要点标签🔗⭐
15 InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning InSpire：通过内禀空间推理增强视觉-语言-动作模型 vision-language-action VLA
16 Think, Reflect, Create: Metacognitive Learning for Zero-Shot Robotic Planning with LLMs 提出基于元认知学习的LLM机器人零样本规划框架，提升复杂任务泛化能力 large language model

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

#题目一句话要点标签🔗⭐
17 A Hierarchical Graph-Based Terrain-Aware Autonomous Navigation Approach for Complementary Multimodal Ground-Aerial Exploration 提出一种基于分层图的地形感知自主导航方法，用于互补的多模态地面-空中探索 traversability multimodal
18 Traversability-aware path planning in dynamic environments 提出Tr-FMM算法，解决动态环境中机器人避开拥挤区域的安全路径规划问题 traversability

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

#题目一句话要点标签🔗⭐
19 APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight APEX：利用物理驱动的任务规划增强LLM的实时洞察力 reinforcement learning large language model ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页