论文标题
Mixline：长匹马双人咖啡搅拌任务的混合增强学习框架
Mixline: A Hybrid Reinforcement Learning Framework for Long-horizon Bimanual Coffee Stirring Task
论文作者
论文摘要
在日常生活中，需要进行双臂协调的咖啡搅拌（需要协调的咖啡搅拌）等双人活动很常见，并且可以用机器人学习。采用强化学习学习这些任务是一个有前途的话题，因为它使机器人能够探索双臂如何共同协调以完成相同的任务。但是，该领域面临两个主要挑战：协调机制和长途任务分解。因此，我们建议使用在线算法分别学习子任务，然后根据离线算法生成的数据将它们组合在一起。我们基于GPU加速ISAAC体育馆建造了一个学习环境。在我们的工作中，双人机器人成功地学会了掌握，握住和举起汤匙和杯子，将它们插入在一起并搅拌咖啡。所提出的方法有可能扩展到其他长匹马的双人任务。
Bimanual activities like coffee stirring, which require coordination of dual arms, are common in daily life and intractable to learn by robots. Adopting reinforcement learning to learn these tasks is a promising topic since it enables the robot to explore how dual arms coordinate together to accomplish the same task. However, this field has two main challenges: coordination mechanism and long-horizon task decomposition. Therefore, we propose the Mixline method to learn sub-tasks separately via the online algorithm and then compose them together based on the generated data through the offline algorithm. We constructed a learning environment based on the GPU-accelerated Isaac Gym. In our work, the bimanual robot successfully learned to grasp, hold and lift the spoon and cup, insert them together and stir the coffee. The proposed method has the potential to be extended to other long-horizon bimanual tasks.
