在实践中塑造:训练车轮直接在硬件中学习快速跳跃
Shaping in Practice: Training Wheels to Learn Fast Hopping Directly in Hardware
摘要:
学习而不是设计机器人控制器可以大大减少所需的工程工作量,同时还强调鲁棒性。尽管在仿真方面取得了相当大的进展,但直接在硬件中应用学习仍然具有挑战性,部分原因是需要探索潜在的不稳定参数。我们探讨了用训练轮塑造奖励景观的概念:对促进学习的物理硬件进行临时修改。我们展示了一个机器人腿安装在繁荣学习跳得快的概念。这种概念验证体现了典型的挑战,如不稳定性和接触,同时足够简单,可以凭经验绘制和可视化奖励景观。根据我们的研究结果,我们提出了三个标准,设计有效的训练轮学习机器人。视频简介可以在https://youtu.be/6iH5E3LrYh8上找到。
英文摘要:
Learning instead of designing robot controllers can greatly reduce engineering effort required, while also emphasizing robustness. Despite considerable progress in simulation, applying learning directly in hardware is still challenging, in part due to the necessity to explore potentially unstable parameters. We explore the concept of shaping the reward landscape with training wheels: temporary modifications of the physical hardware that facilitate learning. We demonstrate the concept with a robot leg mounted on a boom learning to hop fast. This proof of concept embodies typical challenges such as instability and contact, while being simple enough to empirically map out and visualize the reward landscape. Based on our results we propose three criteria for designing effective training wheels for learning in robotics. A video synopsis can be found at https://youtu.be/6iH5E3LrYh8.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。