Robot path planning in uncertain environment using multi-objective particle swarm optimization

这是一篇2013年的文章，不确定环境下的多目标粒子群路径规划
10.1016/j.neucom.2012.09.019
Keywords：Robot path planning、 Particle swarm optimization 、Danger source 、Uncertainty 、Multi- objective optimization

---

ABSTRACT
2种评判标准: the risk degree and the distance of path
带有不确定危险源的路径规划问题被描述为一个带有约束与不确定coefficient的双目标优化问题
Several new operations/ improvements such as the particle update method based on random sampling and uniform mutation, the infeasible archive, the constrained domination relationship based on collision times with obstacles, are incorporated into the proposed algorithm to improve its effectiveness.
Finally, simulation results demonstrate the capability of our method to generate high-quality Pareto optimal paths

---

existing studies have shown the competence of PSO to tackle the planning problems with static obstacles or dynamic obstacles [12–14].
这篇文章基于改进的多目标粒子群优化算法，研究了危险源位置不确定的机器人路径规划问题。However, that work focused on the danger sources with precise positions.
a fuzzy membership function is used to evaluate the risk degree of path.Since we know only the moving ranges of danger sources, in this paper the risk degree of a path is not a precise number but an interval number.
通过这些最后作者把整个动态的路径规划问题变成一个带约束的双目标优化问题。使用PSO求解。
In this algorithm, a new update method of particles based on the random sampling and the uniform mutation is proposed to improve the feasibility of paths.
In order to balance global exploration and local exploitation of the proposed algo- rithm, besides the feasible archive, an infeasible archive is used to save good infeasible solutions.And a dynamic decreasing strategy is also proposed to adjust the probability that particles select their global leaders from the infeasible archive

---

PSO

具体的PSO可以上网查，但是这篇文章与其他pso不同的是，它并不是使用准确的评价指标，是模糊评价指标。

Problem formulation

Modeling of the robot workplace

The method proposed by Sun et al. [17] is adopted to model the robot workplace because of its simplicity and small sensitivity to obstacles’ shapes.快看下面这张图，这篇论文非常非常取巧的，在起点和终点之间画了一条横线，然后对横线按一定间隔区分，每一个line和路径的交点的坐标来表示路径,最后会得到一条折线路径.

折现路径的表示就是PH了

然后这个ph也是有约束的，它的约束就是每一个点都不能和图中的障碍物区域有任何的重叠

Performance criterions

For a path PH, a linear fuzzy function is used to evaluate its risk degree with respect to the i-th danger source ,表示的是第i个危险源，其risk的表达式as follows: