cs.RO（2026-07-27）

📊 共 21 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 Data Pyramid for Embodied Manipulation 提出数据金字塔模型以优化机器人操作数据收集 manipulation dexterous manipulation egocentric
2 τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision 提出τ框架以解决触觉增强视觉-语言-动作模型的学习问题 manipulation JEPA Joint-Embedding Predictive Architecture
3 FloAff-Kitchen: Bridging Navigation and Manipulation via Canonical and Progressive Floor Affordance Learning 提出FloAff-Kitchen框架以解决移动操控中的地面可用性识别问题 manipulation mobile manipulation representation learning ✅
4 NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation 提出NEO框架以实现语言引导的NeRF编辑与机器人操作 manipulation teacher-student distillation
5 Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim 提出个性化情节记忆模块以增强人形机器人Kim的社交能力 humanoid humanoid robot large language model
6 A Case Study on the Acceptance of a Humanoid Robotic Head Employed in Three Public Spaces 提出多模态情感响应的类人机器人以提升公共空间互动 humanoid humanoid robot multimodal
7 DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning 提出DeVA以解决机器人政策学习中的视频与动作预测问题 manipulation policy learning affordance
8 WARL: Wrench-Augmented Reinforcement Learning for Task-Agnostic Learning in Legged Robots 提出Wrench-Augmented强化学习以解决腿部机器人探索能力不足问题 quadruped legged robot reinforcement learning
9 ArmnetBench v0.1: Parallel Real-World Evaluation of Manipulation Policies on a Low-Cost Arm Farm 提出ArmnetBench v0.1以解决机器人操作策略评估瓶颈问题 manipulation bi-manual world model
10 PAC-DP: PAC-Bayesian Diffusion Policy Learning 提出PAC-DP以提升机器人操作任务中的扩展性 manipulation policy learning diffusion policy
11 Effective Parameters, Real Behavior: Renormalization for Robotics -- From Infinite Electron Mass to Sim-to-Real Gap 提出重整化方法以缩小机器人仿真与现实之间的差距 manipulation sim-to-real
12 KAI: A Kinematic-Aware Interface for Data-Efficient Articulated Object Manipulation 提出KAI以解决关节物体操作中的数据效率问题 manipulation policy learning
13 Moving-Horizon Estimation and Nonlinear Model Predictive Control of Cable-Driven Soft Manipulators 提出基于简化Cosserat动力学的MHE-NMPC框架以控制软操纵器 model predictive control
14 SHARE: Towards Head-Mounted AR with User-Centric SLAM in Shared Human-Robot Workspaces 提出SHARE以解决共享人机工作空间中的AR用户延迟问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
15 Embodied GPT-5.1: Evidence of a World Model? 探索GPT-5.1作为物理移动机器人高层控制器的可能性 world model world models large language model
16 FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning 提出FeelWorld以解决触觉信息缺失导致的接触预测问题 world model world models latent dynamics
17 LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments 提出LeapBot-WA以解决WAMs在视觉生成中的瓶颈问题 world model world models world action model ✅
18 Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform 提出持续强化学习框架以解决自主赛车中的泛化问题 reinforcement learning offline RL

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
19 A note on the motion representation and configuration update in time stepping schemes for the constrained rigid body 提出基于SE(3)的刚体运动约束建模方法 motion representation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
20 Quality-Adaptive Multi-UAV 3D Reconstruction with Sparse Workload Redistribution 提出质量自适应的多无人机3D重建方法以解决协调挑战 3D reconstruction

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

#题目一句话要点标签🔗⭐
21 FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking 提出FutureRTC以解决实时机器人执行中的预测与执行不一致问题 vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页