| 1 |
ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models |
提出ACoT-VLA,通过动作链式推理提升VLA模型在机器人操作任务中的性能 |
manipulation policy learning vision-language-action |
|
|
| 2 |
Where to Touch, How to Contact: Hierarchical RL-MPC Framework for Geometry-Aware Long-Horizon Dexterous Manipulation |
提出层级RL-MPC框架,解决几何感知的长程灵巧操作问题 |
manipulation dexterous manipulation sim-to-real |
|
|
| 3 |
A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation |
A3D:基于自适应可供性的双臂协作家具装配框架 |
manipulation dual-arm affordance |
|
|
| 4 |
Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Model |
提出基于液压动力学的执行器模型,实现重型液压四足机器人强化学习控制的迁移。 |
quadruped locomotion locomotion policy |
|
|
| 5 |
Skill-Aware Diffusion for Generalizable Robotic Manipulation |
提出Skill-Aware Diffusion,提升机器人操作的泛化能力 |
manipulation sim-to-real |
|
|
| 6 |
Learning Semantic-Geometric Task Graph-Representations from Human Demonstrations |
提出基于语义-几何任务图表示的学习框架,用于理解双臂操作中的长时程任务 |
manipulation bi-manual representation learning |
|
|
| 7 |
The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning |
发布Mini Wheelbot数据集,助力机器人学习中不平衡系统的鲁棒控制算法开发 |
model predictive control reinforcement learning |
|
|