arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.07779eess.SYcs.SY
收藏

基于学习刚性的高斯过程群集控制

Learning Rigidity-based Flocking Control with Gaussian Processes

Manuela Gamonal, Thomas Beckers, George J. Pappas, Leonardo J. Colombo

摘要:

多智能体系统的群集控制是具有挑战性的部分未知的动态代理。提出了一种基于在线学习的控制器,利用高斯过程(GP)来稳定具有额外未知非线性动力学的双积分智能体的群集运动。智能体交互由一个时不变的无穷小刚性无向图描述。我们提供了一个分散的控制律,指数稳定的代理的运动,并捕捉雷诺boids运动的群体通过使用全球定位系统作为一个在线学习为基础的预言未知的动态预测。特别是,所提出的方法保证了概率有界的跟踪误差具有很高的概率。

英文摘要:

Flocking control of multi-agents system is challenging for agents with partially unknown dynamics. This paper proposes an online learning-based controller to stabilize flocking motion of double-integrator agents with additional unknown nonlinear dynamics by using Gaussian processes (GP). Agents interaction is described by a time-invariant infinitesimally minimally rigid undirected graph. We provide a decentralized control law that exponentially stabilizes the motion of the agents and captures Reynolds boids motion for swarms by using GPs as an online learning-based oracle for the prediction of the unknown dynamics. In particular the presented approach guarantees a probabilistic bounded tracking error with high probability.

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。

↑