cs.RO（2026-07-09）

📊 共 16 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation	提出DexVerse基准以解决多任务多体现的灵巧操作评估问题	manipulation dexterous hand dexterous manipulation	✅
2	Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents	提出Harness VLA以解决语言条件下操控的可靠性问题	manipulation bi-manual bimanual manipulation
3	FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation	提出FabriVLA以解决多任务精确操作问题	manipulation flow matching vision-language-action
4	ContactMimic: Humanoid Object Interaction via Contact Control	提出CONTACTMIMIC以解决机器人与物体交互中的接触控制问题	humanoid manipulation sim2real	✅
5	AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance	提出AnyDexRT以解决无校准灵巧手重定向问题	dexterous hand teleoperation imitation learning	✅
6	Native Video-Action Pretraining for Generalizable Robot Control	提出LingBot-VA 2.0以解决机器人控制中的视频行动模型不足问题	manipulation policy learning foundation model
7	TFP: Temporally Conditioned Memory-Fusion Policies for Visuomotor Learning	提出TFP以解决阶段依赖性操作中的记忆与动态更新问题	manipulation flow matching VLA
8	SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation	提出SkillPlug以解决机器人操作中的少量示范适应问题	manipulation
9	A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths	提出人类相似性与舒适度指数以优化机器人运动	humanoid
10	FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation	提出FabriVLA以解决多任务精确操控问题	manipulation flow matching vision-language-action
11	AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning	提出AgenticFocus以解决人类视频中的物体遮挡问题	humanoid policy learning egocentric
12	FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space	提出FlowDAgger以解决机器人政策适应性不足问题	manipulation bi-manual reinforcement learning	✅

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

#	题目	一句话要点	标签	🔗	⭐
13	FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation	提出FSD-VLN以解决长距离无人机视觉语言导航中的决策延迟问题	VLN multimodal
14	Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN	提出带宽受限的合作视觉语言导航以解决通信效率问题	VLN	✅
15	CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding	提出CLAP以解决VLM与VLA适配问题	vision-language-action VLA

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

#	题目	一句话要点	标签	🔗	⭐
16	SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control	提出SplatCtrl以解决动态环境下机器人控制问题	3D gaussian splatting gaussian splatting splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页