cs.RO（2025-05-17）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗1) 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) (11 篇)

#题目一句话要点标签🔗⭐
1 H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos 提出H2R数据增强方法，弥合人与机器人视觉差异，提升机器人预训练效果 manipulation policy learning egocentric
2 OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning 提出OneTwoVLA，统一视觉-语言-动作模型，提升机器人自适应推理能力 manipulation dexterous manipulation vision-language-action
3 GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation GLOVER++：利用人类行为中的可供性学习提升机器人操作能力 manipulation open-vocabulary open vocabulary
4 Integrating Model-based Control and RL for Sim2Real Transfer of Tight Insertion Policies 提出一种融合模型控制与强化学习的策略，实现高精度插件插入的Sim2Real迁移。 sim2real reinforcement learning zero-shot transfer
5 Human-Centered Development of Guide Dog Robots: Quiet and Stable Locomotion Control 针对视障人士，提出低噪声、稳定步态的导盲犬机器人运动控制方案 quadruped locomotion Unitree
6 Growable and Interpretable Neural Control with Online Continual Learning for Autonomous Lifelong Locomotion Learning Machines 提出GOLLUM以解决持续运动学习中的四大挑战 locomotion
7 PROBE: Proprioceptive Obstacle Detection and Estimation while Navigating in Clutter 提出PROBE，利用本体感觉进行杂乱环境中障碍物检测与估计 quadruped Unitree
8 L2D2: Robot Learning from 2D Drawings L2D2：提出一种基于2D草图的机器人模仿学习方法，降低人工示教成本。 manipulation imitation learning
9 Bench-NPIN: Benchmarking Non-prehensile Interactive Navigation 提出Bench-NPIN，用于评估非抓取交互式导航算法，解决缺乏统一评估标准问题。 manipulation ✅
10 Proactive tactile exploration for object-agnostic shape reconstruction from minimal visual priors 提出一种主动触觉探索方法，从少量视觉先验信息中进行物体形状重建 manipulation
11 Master Rules from Chaos: Learning to Reason, Plan, and Interact from Chaos for Tangram Assembly MRChaos：通过混沌学习推理、规划和交互，解决七巧板拼装机器人难题 manipulation

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

#题目一句话要点标签🔗⭐
12 Gaussian Splatting as a Unified Representation for Autonomy in Unstructured Environments 提出基于高斯溅射的统一表示，用于非结构化环境下的机器人自主导航。 gaussian splatting splatting
13 Online Synthesis of Control Barrier Functions with Local Occupancy Grid Maps for Safe Navigation in Unknown Environments 提出基于局部栅格地图的在线控制屏障函数综合方法，保障未知环境下的安全导航。 occupancy grid

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

#题目一句话要点标签🔗⭐
14 Federated Deep Reinforcement Learning for Privacy-Preserving Robotic-Assisted Surgery 提出联邦深度强化学习框架，解决机器人辅助手术中数据隐私和个性化策略问题 reinforcement learning deep reinforcement learning OMOMO

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

#题目一句话要点标签🔗⭐
15 Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation 提出Aux-Think框架，解决视觉-语言导航中推理策略的数据效率问题。 VLN chain-of-thought

⬅️ 返回 cs.RO 首页 · 🏠 返回主页