| 1 |
MaskedManipulator: Versatile Whole-Body Manipulation |
MaskedManipulator：用于全身操作的多功能物理模拟人形运动生成 |
manipulation whole-body manipulation teleoperation |
|
|
| 2 |
Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments |
提出Omni-Perception，用于腿足机器人动态环境下的全向避障 |
legged locomotion locomotion locomotion policy |
|
|
| 3 |
Towards Humanoid Robot Autonomy: A Dynamic Architecture Integrating Continuous thought Machines (CTM) and Model Context Protocol (MCP) |
提出CTM-MCP动态架构，解决人形机器人在未知场景下的自主行动问题 |
humanoid humanoid robot |
|
|
| 4 |
ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning |
提出ReFineVLA，通过推理引导微调提升VLA模型在机器人操作任务中的性能。 |
manipulation vision-language-action VLA |
|
|
| 5 |
WorldEval: World Model as Real-World Robot Policies Evaluator |
WorldEval：利用世界模型作为真实机器人策略的评估器 |
manipulation world model |
|
|
| 6 |
Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment |
提出一种新型Pin-pression夹爪，并学习其在线手内调整的灵巧抓取技能 |
sim-to-real reinforcement learning curriculum learning |
✅ |
|
| 7 |
Staircase Recognition and Location Based on Polarization Vision |
提出基于偏振视觉的楼梯识别与定位方法，增强机器人和视觉障碍人士的场景感知能力。 |
humanoid humanoid robot scene reconstruction |
|
|
| 8 |
SPADE: Towards Scalable Path Planning Architecture on Actionable Multi-Domain 3D Scene Graphs |
SPADE：面向可操作多域3D场景图的可扩展路径规划架构 |
quadruped |
|
|