Place Classification With a Graph Regularized Deep Neural Network

Abstract

Place classification is a fundamental ability that a robot should possess to carry out effective human-robot interactions. It is a nontrivial classification problem which has attracted many research. In recent years, there is a high exploitation of Artificial Intelligent algorithms in robotics applications. Inspired by the recent successes of deep learning methods, we propose an end-to-end learning approach for the place classification problem. With the deep architectures, this methodology automatically discovers features and contributes in general to higher classification accuracies. The pipeline of our approach is composed of three parts. Firstly, we construct multiple layers of laser range data to represent the environment information in different levels of granularity. Secondly, each layer of data is fed into a deep neural network model for classification, where a graph regularization is imposed to the deep architecture for keeping local consistency between adjacent samples. Finally, the predicted labels obtained from all the layers are fused based on confidence trees to maximize the overall confidence. Experimental results validate the effectiveness of our end-to-end place classification framework in which both the multi-layer structure and the graph regularization promote the classification performance. Furthermore, results show that the features automatically learned from the raw input range data can achieve competitive results to the features constructed based on statistical and geometrical information.

Parse geometry from a line: Monocular depth estimation with partial laser observation

“…Many well-known robots such as Pioneer 1 and K5 Security Robot 2 are equipped with a camera and a 2D laser range finder. The 2D laser range finder is indispensable for navigation and obstacle avoidance on the mobile robot [9], [10]. We demonstrate that our method facilitates greater perception for obstacle avoidance compared to that of a single 2D laser range finder, as the latter has a very limited vertical field of view which might be insufficient to completely reflect the surrounding environments especially with voids.…”

Semantic Mapping Based on Spatial Concepts for Grounding Words Related to Places in Daily Environments

“…Some studies on semantic mapping using two-dimensional (2D) maps such as topological maps (Garg et al, 2017 ; Liao et al, 2017 ; Pronobis and Rao, 2017 ; Luperto and Amigoni, 2018 ; Wang et al, 2018a ) and occupancy grid maps (Goeddel and Olson, 2016 ; Sünderhauf et al, 2016 ; Himstedt and Maehle, 2017 ; Brucker et al, 2018 ; Posada et al, 2018 ; Rangel et al, 2019 ), were also conducted. Wang et al ( 2018a ) proposed a method that constructed a topological semantic map to guide object search.…”

Hierarchical Graph Neural Network Based on Semi-Implicit Variational Inference

“…Different neighbour nodes have different weights, specifying different weights to different nodes in the neighbourhood that can prevent redundant information from being aggregate, hence, Veličković et.al [12] proposed graph attention networks(GATs) use masked self-attentional layers. Besides, based on the GNN, some interesting works were also proposed by scholars, such as graph pool [13], place classification [14], and facial expression recognition [15].…”