基于关系网络的新型学习控制

设计了一种不同于传统智能算法如自适应控制与模糊控制等的智能控制算法，该算法基于目标输入关系网络， 借鉴强化学习的思想，采用输出试探与评价进行学习，是一种模型无关的控制算法，该算法可以与随机优化算法结合，通 过实验，验证了其在控制过程中有效性，并通过与遗传算法结合，验证了与遗传算法相结合的该智能算法的控制效果。

Improved Algorithm of Pure Pursuit Model

A intelligent control algorithm was presented.which was different from traditional intelligent algorithms like adaptive control and fuzzy control. This intelligent control algorithm was based on the target-input relationship network, which learned from reinforcement learning, and used try and evaluation to learn. It was a model-independent control algorithm. This control algorithm could be combined with stochastic optimization algorithms. Experiments verify the effectiveness of this algorithm by combination with genetic algorithms.