提出RT-HCP算法，实现机器人平台高效实时控制。
RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms
- 设计框架解决推理延迟问题，保证控制无间隙
- 在高频率FURUTA摆系统上实现低样本高效学习
- 适合对实时性与样本效率要求高的机器人应用
直接在机器人平台上学习控制器需要极高的样本效率。基于模型的强化学习（RL）方法样本效率最高，但通常推理时间过长，无法满足机器人控制频率要求。本文通过两项贡献应对这一挑战：首先，提出一个通用框架，解决推理延迟问题，使慢速推理控制器能持续输出动作序列，避免执行空档；其次，在该框架下对比多种RL算法，提出RT-HCP算法，在性能、样本效率和推理时间之间取得优异平衡。通过在简单但高频的FURUTA摆平台上进行实验，验证了RT-HCP的优越性。代码已开源：github.com/elasriz/RTHCP。
原文摘要 · Abstract (English)
Learning a controller directly on the robot requires extreme sample efficiency. Model-based reinforcement learning (RL) methods are the most sample efficient, but they often suffer from a too long inference time to meet the robot control frequency requirements. In this paper, we address the sample efficiency and inference time challenges with two contributions. First, we define a general framework to deal with inference delays where the slow inference robot controller provides a sequence of actions to feed the control-hungry robotic platform without execution gaps. Then, we compare several RL algorithms in the light of this framework and propose RT-HCP, an algorithm that offers an excellent trade-off between performance, sample efficiency and inference time. We validate the superiority of RT-HCP with experiments where we learn a controller directly on a simple but high frequency FURUTA pendulum platform. Code: github.com/elasriz/RTHCP
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。