cs.RO（2026-06-26）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation	提出复合人形全身模仿系统以解决稳定行走与灵活操作问题	humanoid humanoid robot whole-body control	✅
2	Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies	提出数据中心化管道以解决人形机器人运动学习问题	humanoid humanoid robot humanoid locomotion
3	S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation	提出S$^2$-VLA以解决长时间操作中的累积误差问题	manipulation vision-language-action VLA
4	CacheMPC: Certified Cached Model Predictive Control for Quadruped Locomotion	提出CacheMPC以解决四足机器人运动控制中的计算效率问题	quadruped locomotion MPC
5	PA-BiCoop: A Primary-Auxiliary Cooperative Framework for General Bimanual Manipulation	提出PA-BiCoop以解决双臂协作中的动态分工问题	manipulation bi-manual bimanual manipulation
6	Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?	提出Drop-Then-Recovery方法以评估视觉-语言-动作模型的冗余性	manipulation vision-language-action VLA	✅
7	Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors	提出Uni-Mo以解决四足机器人运动生成问题	quadruped humanoid locomotion	✅
8	PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control	提出PPO-EAL以解决安全机器人控制中的约束优化问题	quadruped locomotion sim-to-real
9	Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots	提出桥接动作表示以有效转移人类操作技能至机器人	manipulation bi-manual vision-language-action
10	SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation	提出SimFoundry以解决机器人政策训练与评估的挑战	manipulation bi-manual policy learning
11	Learning Stable In-Grasp Manipulation in a Non-Dropping Action Space	提出基于物理理论的稳定抓取操作学习方法	manipulation dexterous manipulation reinforcement learning
12	WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation	提出WARP-RM以解决数据策划中的示范质量问题	manipulation bi-manual teleoperation
13	DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand	提出DexCompose以解决单手多任务操控问题	manipulation dexterous manipulation
14	Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization	提出3D点直接注入机制以解决VLA模型的空间与任务泛化问题	manipulation vision-language-action VLA
15	P-ARC: Exploiting Subproblem Independence for Parallel Multi-Robot Motion Planning	提出P-ARC以解决多机器人运动规划中的并行计算问题	motion planning
16	DIM-WAM: World-Action Modeling with Diverse Historical Event Memory	提出DIM-WAM以解决长时间依赖任务的记忆不足问题	manipulation	✅

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

#	题目	一句话要点	标签	🔗	⭐
17	SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks	提出SpikeVLA以解决低功耗实时智能导航问题	representation learning vision-language-action VLA
18	LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation	提出LocalNav以解决资源受限机器人中的目标导航问题	distillation open-vocabulary open vocabulary

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

#	题目	一句话要点	标签	🔗	⭐
19	Building a Scalable, Reproducible, Evaluatable, and Closed-Loop Simulation Environment Foundation for Embodied Intelligence Cloud-Native Simulation Infrastructure for Embodied Intelligence Training, Evaluation, and Data Collection	提出云原生模拟基础设施以解决机器人数据收集的高成本与低可扩展性问题	VLA
20	When Multi-Robot Systems Meet Agentic AI:Towards Embodied Collective Intelligence	提出具身集体智能以解决多机器人协作问题	embodied AI

⬅️ 返回 cs.RO 首页 · 🏠 返回主页