arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.17620cs.RO
收藏

OCCAM:基于元学习模型的在线连续控制器自适应

OCCAM: Online Continuous Controller Adaptation with Meta-Learned Models

School of Engineering and Applied Science(工程与应用科学学院);University of Pennsylvania(宾夕法尼亚大学)

Hersh Sanghvi, Spencer Folk, Camillo Jose Taylor

AI总结:

提出OCCAM框架,结合元学习与贝叶斯递归估计,在线自适应控制器参数,适用于多种机器人系统,提升性能。

摘要:

控制器的调优与自适应对机器人在多样化环境中的使用构成了重大挑战。通常,通过人工方式找到一组在机器人可能遇到的各种环境和条件下均表现良好的控制参数并非易事。自动化自适应方法必须利用关于系统的先验知识,同时适应显著的领域偏移,以快速找到新的控制参数。在这项工作中,我们提出了一个通用的在线控制器自适应框架来应对这些挑战。我们将元学习与贝叶斯递归估计相结合,学习系统性能的先验预测模型,这些模型即使在存在显著领域偏移的情况下也能快速适应在线数据。这些预测模型可以作为高效基于采样的优化例程中的成本函数,用于在线找到最大化系统性能的新控制参数。我们的框架足够强大且灵活,能够为四个不同的系统自适应控制器:一个模拟赛车、一个模拟四足机器人,以及一个模拟和物理四旋翼飞行器。视频和代码可在 https://hersh500.github.io/occam 获取。

英文摘要:

Control tuning and adaptation present a significant challenge to the usage of robots in diverse environments. It is often nontrivial to find a single set of control parameters by hand that work well across the broad array of environments and conditions that a robot might encounter. Automated adaptation approaches must utilize prior knowledge about the system while adapting to significant domain shifts to find new control parameters quickly. In this work, we present a general framework for online controller adaptation that deals with these challenges. We combine meta-learning with Bayesian recursive estimation to learn prior predictive models of system performance that quickly adapt to online data, even when there is significant domain shift. These predictive models can be used as cost functions within efficient sampling-based optimization routines to find new control parameters online that maximize system performance. Our framework is powerful and flexible enough to adapt controllers for four diverse systems: a simulated race car, a simulated quadrupedal robot, and a simulated and physical quadrotor. The video and code can be found at https://hersh500.github.io/occam.

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。

↑