cs.RO（2026-04-27）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (6 🔗1) 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives	MotionBricks：模块化潜在生成模型与智能原语实现可扩展的实时动作生成。	humanoid humanoid robot Unitree
2	Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation	提出MoT-HRA框架以从大规模人类示范中学习人类意图先验	manipulation scene understanding motion generation
3	AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation	AsyncShield：一种即插即用的边缘适配器，用于异步云端VLA导航	domain randomization reinforcement learning PPO
4	$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills	提出$M^2$-VLA，通过层混合和元技能提升视觉-语言模型在操作任务中的泛化性。	manipulation vision-language-action VLA
5	Betting for Sim-to-Real Performance Evaluation	提出基于博弈论的Sim-to-Real性能评估方法，提升真实机器人性能预测的准确性和效率。	sim-to-real sim2real	✅
6	Multi-Robot Motions in Milliseconds: Vector-Accelerated Primitives for Sampling-Based Planning	提出向量加速的多机器人运动规划方法，实现毫秒级求解	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
7	Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment	针对机器人VLA模型在异构XPU上部署的约束与加速方法研究	vision-language-action VLA
8	FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching	FreqCache：利用自适应频率引导的Token缓存加速具身VLN模型	vision-language-navigation VLN

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

#	题目	一句话要点	标签	🔗	⭐
9	Passage-Aware Structural Mapping for RGB-D Visual SLAM	提出一种通道感知的RGB-D视觉SLAM结构化建图方法，用于增强室内机器人导航。	visual SLAM	✅
10	Event-based SLAM Benchmark for High-Speed Maneuvers	EvSLAM：针对高速运动的事件相机SLAM基准测试框架	visual odometry VIO

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

#	题目	一句话要点	标签	🔗	⭐
11	Agent-Centric Visual Reinforcement Learning under Dynamic Perturbations	提出ACO-MoE框架，解决动态扰动下Agent-Centric视觉强化学习的鲁棒性问题	reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页