Place classification with a graph regularized deep neural network model

by   Yiyi Liao, et al.

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 effective- ness 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.


page 2

page 5

page 10


A Deep Graph Embedding Network Model for Face Recognition

In this paper, we propose a new deep learning network "GENet", it combin...

Brain Signal Classification via Learning Connectivity Structure

Connectivity between different brain regions is one of the most importan...

End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks

In this work we present a novel end-to-end framework for tracking and cl...

Micro-Doppler Based Human-Robot Classification Using Ensemble and Deep Learning Approaches

Radar sensors can be used for analyzing the induced frequency shifts due...

Deep learning from crowds

Over the last few years, deep learning has revolutionized the field of m...

An Analysis of Human-Robot Information Streams to Inform Dynamic Autonomy Allocation

A dynamic autonomy allocation framework automatically shifts how much co...

Nested Learning For Multi-Granular Tasks

Standard deep neural networks (DNNs) are commonly trained in an end-to-e...

Please sign up or login with your details

Forgot password? Click here to reset