用神经网络求解空间中两凸多面体间最短距离

Sovling the Minimum Distance between Two Convex Polyhedron Using Neural Networks

求解空间中两凸多面体间最短距离是机器人规划系统中的普遍问题 ,碰撞检测是它的一个特例 ,目前一般采用梯度映射方法〔1,2〕。提出一种基于人工神经网络的求解空间中两个凸多面体间的最短距离的算法 。

The problem of solving the minimum distance of two convex polyhedron is very popular in robot planning systems,especially in collision detection.Gradiant mapping is widely used in these areas.In this paper,we present a new method based on neural networks.Experimental results show that our method is valid.