cs.RO（2026-01-13）

📊 共 8 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (5) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding	提出基于注意力机制神经地图编码的AME-2框架，实现敏捷且泛化的腿足机器人运动控制。	quadruped legged locomotion biped
2	FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models	FSAG：利用扩散模型增强人手到灵巧手的手指特定可供性抓取	manipulation dexterous hand dexterous manipulation
3	ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation	ActiveVLA：为视觉-语言-动作模型注入主动感知能力，实现精准3D机器人操作	manipulation vision-language-action VLA
4	Real2Sim based on Active Perception with automatically VLM-generated Behavior Trees	提出基于主动感知和VLM自动生成行为树的Real2Sim框架	real2sim
5	Teaching Robots Like Dogs: Learning Agile Navigation from Luring, Gesture, and Speech	提出一种人机协作框架，通过诱导、手势和语音指令，使机器人高效学习敏捷导航。	legged robot multimodal

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

#	题目	一句话要点	标签	🔗	⭐
6	Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving?	提出语义与策略双驱动混合决策框架，提升具身智能驾驶在开放环境下的决策能力	reinforcement learning deep reinforcement learning DRL
7	VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory	提出VLingNav，通过自适应推理和视觉辅助语言记忆实现具身导航。	reinforcement learning imitation learning VLA

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

#	题目	一句话要点	标签	🔗	⭐
8	Large Language Models to Enhance Multi-task Drone Operations in Simulated Environments	提出基于微调CodeT5的自然语言无人机多任务控制方法	large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页