cs.RO（2025-12-19）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning AnyTask：自动化任务与数据生成框架，推进Sim-to-Real策略学习 manipulation sim-to-real motion planning
2 Semantic Co-Speech Gesture Synthesis and Real-Time Control for Humanoid Robots 提出一种基于语义理解的共语姿势生成与人形机器人实时控制框架 humanoid humanoid robot Unitree
3 Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation 提出基于运动学感知的扩散策略，解决机械臂全身操作中的空间泛化问题。 whole-body control manipulation policy learning
4 Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks 提出神经符号控制框架，利用大语言模型解决语言引导的空间任务 manipulation reinforcement learning large language model
5 Flying in Clutter on Monocular RGB by Learning in 3D Radiance Fields with Domain Adaptation 提出基于3D辐射场和对抗域适应的单目RGB图像无人机复杂环境导航方法 sim-to-real 3D gaussian splatting 3DGS
6 UniStateDLO: Unified Generative State Estimation and Tracking of Deformable Linear Objects Under Occlusion for Constrained Manipulation UniStateDLO：提出统一的生成式框架，用于遮挡下可变形线性物体的状态估计与跟踪 manipulation sim-to-real
7 Planning as Descent: Goal-Conditioned Latent Trajectory Synthesis in Learned Energy Landscapes 提出Planning as Descent (PaD)，通过学习能量场进行离线目标条件强化学习。 manipulation reinforcement learning policy learning
8 Vidarc: Embodied Video Diffusion Model for Closed-loop Control Vidarc：用于闭环控制的具身视频扩散模型，提升机器人操作性能。 manipulation cross-embodiment

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

#题目一句话要点标签🔗⭐
9 RecipeMasterLLM: Revisiting RoboEarth in the Era of Large Language Models RecipeMasterLLM：利用大语言模型重塑RoboEarth知识获取流程 large language model
10 A Service Robot's Guide to Interacting with Busy Customers 研究服务机器人与忙碌顾客交互，优化沟通方式以提升用户体验 multimodal

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

#题目一句话要点标签🔗⭐
11 ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination ImagineNav++：通过场景想象提示视觉-语言模型，实现具身导航 open-vocabulary open vocabulary large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页