| 1 |
KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion |
KiVi：用于动态安全足式机器人自中心运动的动觉-视觉空间融合框架 |
quadruped legged robot legged locomotion |
|
|
| 2 |
Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement Learning |
基于引导强化学习的大型软体机器人零样本全身操作 |
manipulation whole-body manipulation sim-to-real |
|
|
| 3 |
DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation |
DexFlyWheel：一种可扩展的、自提升的灵巧操作数据生成框架 |
manipulation dexterous manipulation dual-arm |
|
|
| 4 |
Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models |
提出Oat-VLA，通过对象-智能体中心化Token化，提升VLA模型在机器人操作中的效率。 |
manipulation representation learning vision-language-action |
|
|
| 5 |
HeLoM: Hierarchical Learning for Whole-Body Loco-Manipulation in Hexapod Robot |
提出HeLoM框架，解决六足机器人全身协同重物推移操作难题 |
locomotion manipulation loco-manipulation |
|
|
| 6 |
Control Your Robot: A Unified System for Robot Control and Policy Deployment |
Control Your Robot：统一机器人控制与策略部署的通用系统 |
dual-arm teleoperation policy learning |
|
|
| 7 |
DA-MMP: Learning Coordinated and Accurate Throwing with Dynamics-Aware Motion Manifold Primitives |
提出动力学感知运动流形基元，用于学习协调精准的投掷动作 |
manipulation motion planning flow matching |
|
|
| 8 |
LocoFormer: Generalist Locomotion via Long-context Adaptation |
LocoFormer：通过长程上下文适应实现通用机器人运动控制 |
locomotion domain randomization foundation model |
|
|
| 9 |
Generalizable Coarse-to-Fine Robot Manipulation via Language-Aligned 3D Keypoints |
提出CLAP框架，通过语言对齐的3D关键点实现机器人操作的泛化 |
manipulation |
|
|
| 10 |
MAD-PINN: A Decentralized Physics-Informed Machine Learning Framework for Safe and Optimal Multi-Agent Control |
MAD-PINN：用于安全和最优多智能体控制的去中心化物理信息机器学习框架 |
MPC model predictive control reinforcement learning |
|
|
| 11 |
Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress |
SPARTA：通过视觉空间进度学习操作物体状态变化，解决物体状态操作任务。 |
manipulation reinforcement learning |
|
|
| 12 |
GES-UniGrasp: A Two-Stage Dexterous Grasping Strategy With Geometry-Based Expert Selection |
GES-UniGrasp：基于几何专家选择的两阶段灵巧抓取策略 |
manipulation reinforcement learning |
|
|