تقرير
Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
العنوان: | Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation |
---|---|
المؤلفون: | He, Tairan, Luo, Zhengyi, Xiao, Wenli, Zhang, Chong, Kitani, Kris, Liu, Changliu, Shi, Guanya |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Robotics, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Systems and Control |
الوصف: | We present Human to Humanoid (H2O), a reinforcement learning (RL) based framework that enables real-time whole-body teleoperation of a full-sized humanoid robot with only an RGB camera. To create a large-scale retargeted motion dataset of human movements for humanoid robots, we propose a scalable "sim-to-data" process to filter and pick feasible motions using a privileged motion imitator. Afterwards, we train a robust real-time humanoid motion imitator in simulation using these refined motions and transfer it to the real humanoid robot in a zero-shot manner. We successfully achieve teleoperation of dynamic whole-body motions in real-world scenarios, including walking, back jumping, kicking, turning, waving, pushing, boxing, etc. To the best of our knowledge, this is the first demonstration to achieve learning-based real-time whole-body humanoid teleoperation. Comment: Project website: https://human2humanoid.com/ |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2403.04436 |
رقم الأكسشن: | edsarx.2403.04436 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |