cs.RO（2026-02-17）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching 提出PHP框架，通过运动匹配和深度强化学习，实现人形机器人自主完成复杂环境下的跑酷动作。 humanoid humanoid robot humanoid locomotion
2 MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction MeshMimic：通过3D场景重建实现几何感知的类人运动学习 humanoid humanoid robot reinforcement learning
3 Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation Dex4D：用于灵巧操作的、与任务无关的Sim-to-Real点追踪策略 manipulation dexterous manipulation sim-to-real
4 Selective Perception for Robot: Task-Aware Attention in Multimodal VLA 提出基于任务感知的多模态VLA模型，用于提升机器人操作的效率与鲁棒性。 manipulation vision-language-action VLA
5 One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation 提出基于显式世界表征的MLLM导航框架，提升视觉-语言导航任务性能。 sim-to-real large language model multimodal
6 Fluoroscopy-Constrained Magnetic Robot Control via Zernike-Based Field Modeling and Nonlinear MPC 提出基于Zernike场建模和非线性MPC的荧光透视约束磁力机器人控制方法 MPC model predictive control
7 Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing 提出一种结合空间感知的自适应轨迹优化与控制器引导反馈的自动驾驶赛车框架 trajectory optimization
8 Grip as Needed, Glide on Demand: Ultrasonic Lubrication for Robotic Locomotion 提出超声润滑主动控制摩擦力，实现高效仿生机器人运动 locomotion
9 OSCAR: An Ovipositor-Inspired Self-Propelling Capsule Robot for Colonoscopy OSCAR：一种受产卵器启发的自推进胶囊机器人，用于结肠镜检查 locomotion predictive model
10 Constraining Streaming Flow Models for Adapting Learned Robot Trajectory Distributions 提出约束感知流（CASF）框架，用于自适应机器人轨迹分布并满足约束条件 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
11 ActionCodec: What Makes for Good Action Tokenizers ActionCodec：面向VLA优化的动作Tokenizer设计，提升训练效率与性能 vision-language-action VLA multimodal
12 Improving MLLMs in Embodied Exploration and Question Answering with Human-Inspired Memory Modeling 提出基于人类记忆建模的MLLM框架，提升具身探索和问答能力 large language model multimodal
13 Robot-Assisted Social Dining as a White Glove Service 提出白手套服务原则，设计餐厅场景下辅助用餐机器人系统 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
14 Feasibility-aware Imitation Learning from Observation with Multimodal Feedback 提出FABCO，通过多模态反馈实现可行性感知的观察模仿学习。 policy learning imitation learning behavior cloning
15 Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures 提出基于物理感知的神经架构，加速多旋翼飞行器控制策略的跨平台迁移学习。 reinforcement learning policy learning cross-embodiment

⬅️ 返回 cs.RO 首页 · 🏠 返回主页