Recent years have seen a surge in commercially-available and affordable quadrupedal robots, with many of these platforms being actively used in research and industry. As the availability of legged robots grows, so does the need for controllers that enable these robots to perform useful skills. However, most learning-based frameworks for controller development focus on training robot-specific controllers, a process that needs to be repeated for every new robot. In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots with similar morphologies. We present a simple but effective morphology randomization method that procedurally generates a diverse set of simulated robots for training. We show that by training a controller on this large set of simulated robots, our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots with diverse morphologies, which were not observed during training.
翻译:近些年来,商业上可买得起的四重机器人激增,许多这些平台被积极用于研究和工业。随着腿型机器人的可用性增加,对使这些机器人能够发挥有用技能的控制器的需求也随之增加。然而,大多数基于学习的控制器开发框架都侧重于培训机器人专用控制器,这是每个新机器人都需要重复的一个过程。在这项工作中,我们引入了一个框架,用于培训四重机器人的通用 Locomotion(GenLoco)控制器。我们的框架合成了一般用途的移动控制器,这些控制器可以部署在多种具有类似形态的四重机械上。我们提出了一个简单而有效的形态随机化方法,在程序上生成了一套不同的模拟机器人来进行培训。我们通过对这批大型模拟机器人的管理员进行培训,我们模型获得了更普遍的控制策略,可以直接转移到新型的模拟和真实世界机器人,这些机器人具有不同的形态,在培训期间没有观察到。