Machine learning guided exploration for sampling-based motion planning algorithms
Machine learning guided exploration for sampling-based motion planning algorithms
复制标题
机器学习引导探索基于采样的运动规划算法
DOI：
10.1109/iros.2015.7353738
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
P. Tsiotras
中科院分区：
文献类型：
--
作者：
O. Arslan;P. Tsiotras
我们提出一种受机器学习（ML）启发的方法，用于在基于采样的路径规划器的探索阶段估计运动规划问题的相关区域。该算法引导探索，使得随着迭代次数的增加，从相关区域抽取更多的样本。该方法分两步进行：首先，在不调用碰撞检查器的情况下预测给定样本是否无碰撞（分类阶段），然后在不解决局部转向问题的情况下估计它是否是一个有希望的样本，即它是否有可能改进当前的最佳解决方案（回归阶段）。所提出的探索策略被集成到RRT#算法中。数值模拟证明了所提出方法的有效性。
We propose a machine learning (ML)-inspired approach to estimate the relevant region of a motion planning problem during the exploration phase of sampling-based path-planners. The algorithm guides the exploration so that it draws more samples from the relevant region as the number of iterations increases. The approach works in two steps: first, it predicts if a given sample is collision-free (classification phase) without calling the collision-checker, and it then estimates if it is a promising sample, i.e., if it has the potential to improve the current best solution (regression phase), without solving the local steering problem. The proposed exploration strategy is integrated to the RRT# algorithm. Numerical simulations demonstrate the efficiency of the proposed approach.