cs.RO(2025-12-05)

📊 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) (7) 支柱八:物理动画 (Physics-based Animation) (3) 支柱七:动作重定向 (Motion Retargeting) (1 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (1) 支柱二:RL算法与架构 (RL & Architecture) (1)

🔬 支柱一:机器人控制 (Robot Control) (7 篇)

#题目一句话要点标签🔗
1 WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving 提出WAM-Flow,通过离散流匹配实现自动驾驶并行粗到精运动规划。 motion planning flow matching vision-language-action
2 Situation-Aware Interactive MPC Switching for Autonomous Driving 提出情境感知交互式MPC切换策略,提升自动驾驶交互场景性能并降低计算成本 MPC model predictive control
3 Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning 提出面向对应关系的模仿学习框架COIL,实现灵活的3D视觉运动控制。 manipulation policy learning imitation learning
4 An Integrated System for WEEE Sorting Employing X-ray Imaging, AI-based Object Detection and Segmentation, and Delta Robot Manipulation 提出集成X射线成像、AI检测分割与Delta机器人的WEEE分拣系统 manipulation
5 SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models SIMPACT:利用视觉-语言模型和仿真进行动作规划,解决机器人操作中物理理解不足的问题 manipulation world model
6 GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant For Blind Travelers GuideNav:面向视障人士的纯视觉机器人导航辅助系统,通过用户研究指导开发。 quadruped
7 Probabilistic Weapon Engagement Zones for a Turn Constrained Pursuer 针对转弯约束追击者,提出概率武器交战区(CSPEZ)方法以降低规避风险 trajectory optimization

🔬 支柱八:物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗
8 Real-Time Spatiotemporal Tubes for Dynamic Unsafe Sets 提出实时时空管道框架,解决动态环境中未知动力学系统的安全导航问题 spatiotemporal
9 Spatiotemporal Tubes for Differential Drive Robots with Model Uncertainty 针对模型不确定性差速驱动机器人,提出时空管道控制框架以保证时序可达-避免-停留规范 spatiotemporal
10 Physically-Based Simulation of Automotive LiDAR 提出基于物理的汽车激光雷达仿真模型,系统地确定模型参数,并验证于真实LiDAR系统。 PULSE

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
11 HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies 提出HiMoE-VLA,解决具身智能中异构机器人数据泛化问题。 cross-embodiment vision-language-action VLA

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

#题目一句话要点标签🔗
12 Training-Time Action Conditioning for Efficient Real-Time Chunking 提出训练时动作条件反射,高效实现视觉-语言-动作模型的实时分块控制 vision-language-action VLA

🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗
13 Toward Efficient and Robust Behavior Models for Multi-Agent Driving Simulation 提出一种高效鲁棒的多智能体驾驶行为模型,用于驾驶模拟。 reinforcement learning inverse reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页