Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM

Abstract

The ability to decide if a solution to a pose-graph problem is globally optimal is of high significance for safety-critical applications. Converging to a local-minimum may result in severe estimation errors along the estimated trajectory. In this paper, we propose a graph neural network based on a novel implementation of a graph convolutional-like layer, called PoseConv, to perform classification of posegraphs as optimal or sub-optimal. The operation of PoseConv required incorporating a new node feature, referred to as cost, to hold the information that the nodes will communicate. A training and testing dataset was generated based on publicly available bench-marking pose-graphs. The neural classifier is then trained and extensively tested on several subsets of the pose-graph samples in the dataset. Testing results have proven the model's capability to perform classification with 92−98% accuracy, for the different partitions of the training and testing dataset. In addition, the model was able to generalize to previously unseen variants of pose-graphs in the training dataset. Our method trades a small amount of accuracy for a large improvement in processing time. This makes it faster than other existing methods by up-to three orders of magnitude, which could be of paramount importance when using computationally-limited robots overseen by human operators.

RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization

“…The sparse bounded degree sum-of-squares (Sparse-BSOS) optimization method [22], formulate SLAM problems as polynomial optimization programs and demonstrate the ability to achieve global minimum solutions without initialization. A deep learning approach for pose-graph global optimality classification was also recently proposed in [9].…”

“…We adopt the architecture proposed in [9], formally presented for the task of global optimality prediction. The poses or in other words, nodes of each graph input, store a cost feature and the absolute orientation R i of the node itself.…”

“…( 6). Further provided by [9], once the input pose-graph observation passes forward, a two step process occurs. The first step is the message passing step which involves computing the Frobenius norm of the absolute orientations shared by each edge, where β is a learnable weight:…”

“…The proposed modular encoder-agent architecture is comprised of two main components. The first component is a neural network initially proposed in [9] for graph optimality classification. The second is a recurrent-based soft actorcritic (SAC) [10] agent whose policy predicts the optimal orientation retractions [7].…”

Neural Network Classifier Improvements Based on Ant Colony Algorithm

“…The number of training times required for sample data can be very small, so the RLC NN model can complete unsupervised learning efficiently and quickly, and can classify high-risk data. However, due to the lack of prior knowledge, the optimal kernel parameters cannot generally be found, and the kernel space classifier cannot be completely guaranteed to be linearly separable, resulting in the limitations of the linear classification algorithm for optimizing the output of the RBF network [4][5]. On the whole, the classifiers established by the NN have their own advantages and disadvantages, and it is necessary to further improve the performance of the classifier to improve the classification effect.…”