cs.RO(2025-02-20)

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一:机器人控制 (Robot Control) (8 🔗2) 支柱三:空间感知与语义 (Perception & Semantics) (1) 支柱九:具身大模型 (Embodied Foundation Models) (1) 支柱六:视频提取与匹配 (Video Extraction) (1)

🔬 支柱一:机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗
1 Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration Humanoid-VLA:通过视觉融合实现通用人形机器人控制 humanoid humanoid robot humanoid control
2 ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model ChatVLA:通过视觉-语言-动作模型实现统一的多模态理解和机器人控制 manipulation vision-language-action VLA
3 Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control 提出基于运动自适应和阻抗控制的Sim-to-Real强化学习方法,用于通用铰接物体操作 manipulation sim-to-real motion planning
4 VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception VB-Com:针对感知缺陷,学习类人机器人视觉盲走混合运动控制 legged locomotion humanoid humanoid robot
5 DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectories DDAT:扩散策略通过动态可容许轨迹生成实现机器人运动规划 Unitree diffusion policy multimodal
6 Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions 提出基于神经控制屏障函数的采样MPC算法,提升非线性系统安全性和实时性 MPC model predictive control
7 Getting SMARTER for Motion Planning in Autonomous Driving Systems SMARTS 2.0:用于自动驾驶运动规划的仿真平台与基准测试 motion planning
8 DEFT: Differentiable Branched Discrete Elastic Rods for Modeling Furcated DLOs in Real-Time 提出DEFT,用于实时建模和操作分支DLO,解决线束装配难题 manipulation

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

#题目一句话要点标签🔗
9 Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting 提出Hier-SLAM++,一种基于分层类别高斯溅射的神经符号语义SLAM方法,适用于RGB-D和单目输入。 3D gaussian splatting gaussian splatting splatting

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

#题目一句话要点标签🔗
10 REFLEX Dataset: A Multimodal Dataset of Human Reactions to Robot Failures and Explanations REFLEX数据集:用于研究人-机器人协作中失败与解释的多模态反应数据集 multimodal

🔬 支柱六:视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗
11 Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation Mem2Ego:利用全局到自我的记忆增强视觉语言模型,用于长时程具身导航 egocentric large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页