cs.RO（2025-03-26）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (7 篇)

#题目一句话要点标签🔗⭐
1 MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation 提出MoLe-VLA，通过动态层跳跃和知识蒸馏提升机器人操作效率和性能。 manipulation distillation vision-language-action
2 TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion 提出TAR框架，通过对比学习对齐教师表征，提升四足机器人运动泛化性。 quadruped locomotion reinforcement learning
3 DBaS-Log-MPPI: Efficient and Safe Trajectory Optimization via Barrier States 提出DBaS-Log-MPPI算法，通过离散障碍状态提升复杂环境下轨迹优化安全性与效率。 MPC model predictive control trajectory optimization
4 Combining Machine Learning and Sampling-Based Search for Multi-Goal Motion Planning with Dynamics 结合机器学习与采样搜索，解决动态约束下多目标运动规划问题 motion planning
5 Anti Robot Speciesism 揭示“反机器人”物种歧视：人类倾向于否认拟人机器人的人性 humanoid humanoid robot
6 Turning Circle-based Control Barrier Function for Efficient Collision Avoidance of Nonholonomic Vehicles 提出基于回旋圆的控制屏障函数，提升非完整车辆避障效率 MPC model predictive control
7 Beyond Visuals: Investigating Force Feedback in Extended Reality for Robot Data Collection 探索力反馈在XR机器人数据采集中的作用，提升高精度操作性能 manipulation

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

#题目一句话要点标签🔗⭐
8 Learning Adaptive Dexterous Grasping from Single Demonstrations AdaDexGrasp：基于单次演示学习自适应灵巧抓取 reinforcement learning curriculum learning zero-shot transfer

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

#题目一句话要点标签🔗⭐
9 LGR: LLM-Guided Ranking of Frontiers for Object Goal Navigation LGR：基于LLM引导的前沿探索排序，用于物体目标导航 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
10 Immersive and Wearable Thermal Rendering for Augmented Reality 为增强现实提出沉浸式可穿戴热渲染设备，提升交互真实感 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页