cs.RO（2025-12-02）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 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) (7 篇)

#题目一句话要点标签🔗⭐
1 RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning RoboWheel：利用真实人类演示数据驱动跨形态机器人学习的数据引擎 humanoid dexterous hand domain randomization
2 Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach 提出TACO：一种测试时缩放框架，用于提升VLA模型在下游任务中的稳定性和成功率 dual-arm teleoperation reinforcement learning
3 Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling Video2Act：利用机器人时空运动建模的双系统视频扩散策略 manipulation policy learning diffusion policy
4 Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols ViFailback：利用视觉符号诊断、纠正和学习机器人操作失败 manipulation vision-language-action VLA ✅
5 SwarmDiffusion: End-To-End Traversability-Guided Diffusion for Embodiment-Agnostic Navigation of Heterogeneous Robots SwarmDiffusion：端到端可通行性引导的扩散模型，用于异构机器人通用导航 quadruped traversability cross-embodiment
6 CogDrive: Cognition-Driven Multimodal Prediction-Planning Fusion for Safe Autonomy CogDrive：认知驱动的多模态预测-规划融合，保障自动驾驶安全 trajectory optimization multimodal
7 Experimental Characterization of Fingertip Trajectory following for a 3-DoF Series-Parallel Hybrid Robotic Finger 针对灵巧操作，提出一种基于混合结构的3自由度机器人手指末端轨迹跟踪方法 manipulation dexterous manipulation in-hand manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
8 Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments 提出基于分层强化学习和均值场理论的多智能体足球决策框架 reinforcement learning PPO
9 Vehicle Dynamics Embedded World Models for Autonomous Driving 提出车辆动力学嵌入的世界模型，提升自动驾驶在车辆参数变化下的泛化性与鲁棒性 world model dreamer
10 SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction SAM2Grasp：通过提示条件的时间动作预测解决多模态抓取问题 imitation learning multimodal
11 AID: Agent Intent from Diffusion for Multi-Agent Informative Path Planning 提出AID框架，利用扩散模型进行多智能体信息路径规划，提升效率与信息增益。 reinforcement learning behavior cloning diffusion policy ✅

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

#题目一句话要点标签🔗⭐
12 Reframing Human-Robot Interaction Through Extended Reality: Unlocking Safer, Smarter, and More Empathic Interactions with Virtual Robots and Foundation Models 利用扩展现实重构人机交互，实现更安全、智能和共情的虚拟机器人交互 large language model foundation model multimodal
13 VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling 针对VLA模型泛化性不足，提出轻量级视觉表征校准方法，显著提升视角泛化能力。 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🔗⭐
14 VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM VIGS-SLAM：视觉惯性融合的3D高斯溅射SLAM，实现鲁棒实时跟踪和高保真重建。 3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页