在建立前视声呐视域模型和人工势场模型的基础上，对AUV进行决策控制，通过梯度逼近法对目标进行搜索，快速规划出一条无碰撞的路径。

On the basis of building forward looking sonar view model and artificial potential model, decision control of AUV is made, objects are searched through grads approach, a collision free path is planed.

youdao

本文分析了梯度辨识算法跟踪时变系统的缺点，提出了一种新的基于局部多项式逼近的变参数梯度估计算法。

The trackability limitation of current gradient algorithm is discussed. A new algorithm, named variable parameter gradient estimation algorithm with local polynomial approximation is proposed.

youdao

然后利用这种模式的特点，在线优化算法相结合的策略梯度估计及随机逼近而得。

Then by utilizing the features of this model an online optimization algorithm that combines policy gradient estimation and stochastic approximation is derived.

youdao