cs.RO（2025-12-18）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion E-SDS：环境感知强化学习，提升人形机器人复杂地形运动能力 humanoid humanoid locomotion locomotion
2 Lang2Manip: A Tool for LLM-Based Symbolic-to-Geometric Planning for Manipulation Lang2Manip：基于LLM的符号到几何操作规划工具 manipulation motion planning large language model
3 PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence 提出PhysBrain，利用人类第一视角数据提升机器人物理智能。 humanoid humanoid robot egocentric
4 VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation VERM：利用基础模型创建虚拟视点，提升3D机器人操作效率 manipulation foundation model
5 ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation ManiLong-Shot：交互感知的单样本模仿学习用于长时程操作任务 manipulation imitation learning
6 ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning ReinforceGen：结合自动数据生成与强化学习的混合技能策略，解决机器人长时程操作难题 manipulation motion planning reinforcement learning
7 Sceniris: A Fast Procedural Scene Generation Framework Sceniris：一种快速程序化场景生成框架，加速物理AI和生成模型开发。 manipulation spatial relationship ✅
8 A Task-Driven, Planner-in-the-Loop Computational Design Framework for Modular Manipulators 提出任务驱动的模块化机械臂计算设计框架，实现形态与运动的协同优化 model predictive control motion planning
9 Single-View Shape Completion for Robotic Grasping in Clutter 提出基于扩散模型的单视角形状补全方法，提升机器人抓取性能 manipulation

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

#题目一句话要点标签🔗⭐
10 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future 综述性论文：面向自动驾驶的视觉-语言-动作模型研究进展与未来展望 vision-language-action VLA large language model
11 PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies PolaRiS：用于通用机器人策略的可扩展真实到模拟评估框架 foundation model
12 Real-Time Human-Robot Interaction Intent Detection Using RGB-based Pose and Emotion Cues with Cross-Camera Model Generalization 提出一种基于RGB的姿态与情感融合的实时人机交互意图检测方法，并实现跨摄像头泛化。 multimodal

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

#题目一句话要点标签🔗⭐
13 A2VISR: An Active and Adaptive Ground-Aerial Localization System Using Visual Inertial and Single-Range Fusion 提出A2VISR，融合视觉惯导与单点测距，提升复杂环境下无人机定位鲁棒性 optical flow

⬅️ 返回 cs.RO 首页 · 🏠 返回主页