cs.RO（2026-07-28）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models 提出SAM3D引导的物体中心3D表示对齐框架以解决VLA模型的3D理解问题 manipulation sam 3D SAM 3D
2 Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics 提出物理感知的端到端深度强化学习以解决四旋翼控制问题 actuator dynamics reinforcement learning deep reinforcement learning
3 S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information 提出S2A2框架以解决机器人模仿任务中的声学信息利用问题 manipulation imitation learning diffusion policy
4 HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone 提出HiFi-UMI以解决高保真数据稀缺问题 manipulation teleoperation world action model
5 Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design 提出Transformer Transformer以解决机器人运动条件设计问题 quadruped humanoid manipulation
6 A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models 提出因果感知的IDR框架以解决VLA模型的测试时模态适应问题 manipulation vision-language-action VLA
7 Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations 提出DR-LfD框架以解决机器人灵巧操作中的规划问题 manipulation motion planning imitation learning ✅
8 Tri-Manual Visuomotor Imitation Learning of Robot Policies 提出TriManPolicy以解决三手臂机器人控制不匹配问题 bi-manual teleoperation imitation learning
9 When Does Legacy Data Start to Help? Emergent Transfer in Cross-Configuration Robot Learning 提出跨配置机器人学习中的遗留数据利用策略 humanoid manipulation dual-arm
10 P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning 提出P^3以解决VAE与PPO结合中的不稳定性问题 humanoid parkour PPO ✅
11 DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models 提出DC-WAM以解决视觉预测在控制中的不足问题 manipulation flow matching

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
12 SONG: A Photorealistic 3D Gaussian Simulation Platform for Benchmarking Social Navigation 提出SONG平台以解决社交导航中的视觉观察问题 3D gaussian splatting 3DGS gaussian splatting
13 Leveraging Semantic Maps for City-Scale Cross-View Localization 利用语义地图解决城市规模的跨视角定位问题 semantic map egocentric ✅
14 Room-Mediated Co-occurrence for Zero-Shot Object-Centric Semantic Navigation via Frontier Scoring 提出基于房间介导共现的零-shot物体中心语义导航方法 open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
15 INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models 提出INTACT以解决搜索成本高的问题 world model world models JEPA
16 Cooperative Multi-UAV Navigation in Complex Environments via Systematic Multi-Agent Deep Reinforcement Learning 提出多智能体深度强化学习框架以解决多无人机协作导航问题 reinforcement learning deep reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页