Efficient Mobile Robot Exploration with Gaussian Markov Random Fields in 3D Environments

In this paper, we study the problem of autonomous exploration in unknown indoor environments using mobile robot. We use mutual information (MI) to evaluate the information the robot would get at a certain location. In order to get the most informative sensing location, we first propose a sampling method that can get random sensing patches in free space. Each sensing patch is extended to informative locations to collect information with true values. Then we use Gaussian Markov Random Fields (GMRF) to model the distribution of MI in environment. Compared with the traditional methods that employ Gaussian Process (GP) model, GMRF is more efficient. MI of every sensing location can be estimated using the training sample patches and the established GMRF model. We utilize an efficient computation algorithm to estimate the GMRF model hyperparameters so as to speed up the computation. Besides the information gain of the candidates regions, the path cost is also considered in this work. We propose a utility function that can balance the path cost and the information gain the robot would collect. We tested our algorithm in both simulated and real experiment. The experiment results demonstrate that our proposed method can explore the environment efficiently with relatively shorter path length.

在本文中，我们研究了使用移动机器人在未知室内环境中进行自主探索的问题。我们利用互信息（MI）来评估机器人在某一位置将获取的信息。为了获得信息最丰富的感知位置，我们首先提出一种采样方法，该方法能够在自由空间中获取随机感知区域。每个感知区域都扩展到有信息的位置以收集具有真实值的信息。然后我们使用高斯马尔可夫随机场（GMRF）对环境中互信息的分布进行建模。与采用高斯过程（GP）模型的传统方法相比，GMRF更高效。利用训练样本区域和已建立的GMRF模型可以估计每个感知位置的互信息。我们使用一种高效的计算算法来估计GMRF模型的超参数以加快计算速度。除了候选区域的信息增益外，本文还考虑了路径成本。我们提出了一个效用函数，它能够平衡路径成本和机器人将收集的信息增益。我们在模拟和真实实验中对我们的算法进行了测试。实验结果表明，我们所提出的方法能够以相对较短的路径长度高效地探索环境。