| 1 |
Scalable and General Whole-Body Control for Cross-Humanoid Locomotion |
提出XHugWBC框架，实现通用人形机器人全身控制的跨形态泛化 |
humanoid humanoid robot humanoid control |
|
|
| 2 |
A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion |
提出一种混合自编码器，用于从融合的激光雷达和深度数据中稳健生成高度图，应用于人形机器人运动。 |
humanoid humanoid robot locomotion |
|
|
| 3 |
DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter |
提出DECO：解耦多模态扩散Transformer，用于灵巧双臂操作，并集成触觉适配器 |
manipulation dexterous manipulation bi-manual |
|
|
| 4 |
TOLEBI: Learning Fault-Tolerant Bipedal Locomotion via Online Status Estimation and Fallibility Rewards |
TOLEBI：通过在线状态估计和容错奖励学习具有容错能力的两足行走 |
humanoid humanoid robot bipedal |
|
|
| 5 |
MobileManiBench: Simplifying Model Verification for Mobile Manipulation |
MobileManiBench：简化移动操作机器人模型验证的大规模基准测试 |
manipulation mobile manipulation dexterous hand |
|
|
| 6 |
Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework |
提出PAiD框架，解决人型机器人足球技能学习中感知-动作集成难题 |
humanoid humanoid robot sim-to-real |
✅ |
|
| 7 |
Benchmarking Affordance Generalization with BusyBox |
提出BusyBox基准，用于评估VLA模型在操作新物体时的泛化能力 |
bi-manual affordance vision-language-action |
✅ |
|
| 8 |
RoboPaint: From Human Demonstration to Any Robot and Any View |
RoboPaint：通过人类演示，为任意机器人和视角生成可执行的训练数据。 |
manipulation dexterous manipulation teleoperation |
|
|
| 9 |
HiCrowd: Hierarchical Crowd Flow Alignment for Dense Human Environments |
HiCrowd：面向密集人群环境的分层人群流对齐机器人导航方法 |
MPC model predictive control reinforcement learning |
|
|
| 10 |
TaSA: Two-Phased Deep Predictive Learning of Tactile Sensory Attenuation for Improving In-Grasp Manipulation |
TaSA：用于提升抓取操作的触觉感觉衰减双阶段深度预测学习 |
manipulation dexterous manipulation in-hand manipulation |
|
|
| 11 |
Residual Reinforcement Learning for Waste-Container Lifting Using Large-Scale Cranes with Underactuated Tools |
提出残差强化学习方法，提升欠驱动起重机废弃物抓取的精度和鲁棒性。 |
domain randomization reinforcement learning PPO |
|
|
| 12 |
Visuo-Tactile World Models |
提出Visuo-Tactile World Models，解决接触密集型任务中视觉信息不足的问题。 |
manipulation world model |
|
|