| 1 |
Learning Humanoid Standing-up Control across Diverse Postures |
提出HoST框架，实现人型机器人从多样姿势中学习站立控制，并成功迁移至真实环境。 |
humanoid humanoid robot locomotion |
✅ |
|
| 2 |
COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping |
提出COMBO-Grasp，解决双臂机器人遮挡环境下抓取问题 |
manipulation bi-manual bimanual manipulation |
|
|
| 3 |
A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards |
提出IKER框架，利用VLM生成迭代关键点奖励，实现机器人操作的Real-to-Sim-to-Real迁移。 |
manipulation sim-to-real reinforcement learning |
|
|
| 4 |
CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World |
CordViP：基于对应关系的灵巧操作策略，解决真实场景下的机器人操作难题 |
manipulation dexterous hand dexterous manipulation |
✅ |
|
| 5 |
Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation |
提出RE$^3$SIM，通过3D逼真重建实现机器人操作的真实到仿真数据生成。 |
manipulation sim-to-real imitation learning |
✅ |
|
| 6 |
MuJoCo Playground |
MuJoCo Playground：开源机器人学习框架，加速仿真到真实世界的迁移 |
quadruped humanoid dexterous hand |
|
|
| 7 |
Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery |
提出基于扩散策略的模仿学习方法，解决多物体抓取与放置问题 |
teleoperation imitation learning diffusion policy |
|
|
| 8 |
Acoustic Wave Manipulation Through Sparse Robotic Actuation |
提出基于稀疏机器人驱动的声波调控方法，用于声能聚焦与抑制。 |
manipulation |
✅ |
|
| 9 |
Bilevel Learning for Bilevel Planning |
提出IVNTR，一种神经符号双层学习框架，用于机器人双层规划，实现高泛化性。 |
manipulation mobile manipulation |
|
|