Examination Committee

Prof Shaojie SHEN, ECE/HKUST (Chairperson)
Prof Zexiang LI, ECE/HKUST (Thesis Supervisor)
Prof Ming LIU, ECE/HKUST (Thesis Co-supervisor)
Prof Lu FANG, ECE/HKUST
 

Abstract

The perception and exploration problem are two of the fundamental problems of mobile robots. Perception is a preliminary step and solves recognition problems such as object recognition and scene recognition while the exploration problem has more to do with decision making and control. During the past few years, deep learning has made many breakthroughs in both natural language processing as well as computer vision. Deep neural networks take a hierarchical structure that imitates human brains for information processing and avoids the need to calculate hand crafted features, which brings about many possible solutions to robotic problems. This work introduces an integrated framework for both perception and exploration of mobile robots, with the use of deep neural networks, and focuses on real-time performance, which is essential for robotic applications. A deep insight of the hidden structure of deep neural networks as well as statistical analysis is made. Then a principal component analysis (PCA)-based algorithm is proposed for the efficient execution of deep neural networks. The structure is tested for image classification problems, considering both pixel-wise classification and patch-wise classification. Furthermore, an indoor exploration approach is proposed and tested in both simulated and real world environment, considering noise observation and performance is evaluated