| 1 |
The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive Dynamics |
提出基于被动动力学的杜克人形机器人,实现高能效双足行走 |
humanoid bipedal biped |
|
|
| 2 |
Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning |
提出一种基于多模态强化学习的四足机器人避障运动控制方法 |
quadruped locomotion reinforcement learning |
|
|
| 3 |
Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning |
提出基于图神经网络的去中心化无标签运动规划方法,提升多机器人系统的可扩展性。 |
motion planning reinforcement learning imitation learning |
|
|
| 4 |
LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World |
LiRA:一种轻量鲁棒的对抗学习框架,用于真实世界中基于模型的强化学习 |
quadruped gait control reinforcement learning |
|
|
| 5 |
Learning Wheelchair Tennis Navigation from Broadcast Videos with Domain Knowledge Transfer and Diffusion Motion Planning |
提出基于扩散运动规划的零样本知识迁移框架,用于轮椅网球导航 |
motion planning imitation learning |
|
|
| 6 |
Lessons Learned from Developing a Human-Centered Guide Dog Robot for Mobility Assistance |
开发以人为本的导盲机器人,提升视障人士的出行辅助 |
quadruped |
|
|
| 7 |
GelSlim 4.0: Focusing on Touch and Reproducibility |
GelSlim 4.0:面向触觉感知与可复现性的开源视觉触觉传感器 |
manipulation |
|
|
| 8 |
Multi-Query Shortest-Path Problem in Graphs of Convex Sets |
提出基于凸集图的多查询最短路径方法,加速机器人臂运动规划。 |
motion planning |
|
|