Point set registration has been a topic of significant research interest in the field of mobile intelligent unmanned systems. In this paper, we present a novel approach for a three-dimensional scan-to-map point set registration. Using Gaussian process (GP) regression, we propose a new type of map representation, based on a regionalized GP map reconstruction algorithm. We combine the predictions and the test locations derived from the GP as the predictive points. In our approach, the correspondence relationships between predictive point pairs are set up naturally, and a rigid transformation is calculated iteratively. The proposed method is implemented and tested on three standard point set datasets. Experimental results show that our method achieves stable performance with regard to accuracy and efficiency, on a par with two standard methods, the iterative closest point algorithm and the normal distribution transform. Our mapping method also provides a compact point-cloud-like map and exhibits low memory consumption.

在移动智能无人系统领域中，点集注册一直是一个重要的研究课题。在本文中，我们为三维扫描到地图的点集配准提供了一种新颖的方法。使用高斯过程（GP）回归，我们基于区域化GP地图重构算法提出了一种新型的地图表示形式。我们将预测和从GP得出的测试位置结合起来作为预测点。在我们的方法中，自然建立了预测点对之间的对应关系，并迭代计算了一个刚性变换。所提出的方法在三个标准点集数据集上实现和测试。实验结果表明，与两种标准方法相比，我们的方法在准确性和效率方面都达到了稳定的性能，迭代最近点算法和正态分布变换。我们的映射方法还提供了一个紧凑的点云状映射，并且内存消耗低。