(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Embedded artificial intelligent (ai) To navigate cart follower

Embedded artificial intelligent (ai) To navigate cart follower / Tang khai luen
Usaha masyarakat dalam menwujudkan kehidupan yang berkualiti setiap individu tanpa mengetepikan hak orang kurang upaya mendorong kewujudan penyelidikan mengenai reka bentuk dan fabrikasi robot autonomi. Pengguna kerusi roda biasanya menghadapi masalah membawa bagasi semasa perjalanan kerana mereka memerlukan kedua-dua tangan mereka untuk menavigasi kerusi roda mereka. Salah satu penyelesaian untuk masalah ini adalah untuk mencipta pengikut troli Artificial Intelligent (AI). Oleh itu, penyelidikan ini adalah untuk mewujudkan sistem AI untuk pengikut troli AI dengan sensor berasaskan visual. Sensor berasaskan visual mengumpul maklumat mengenai panjang, tinggi, x dan y koordinasi papan corak warna yang terletak di belakang kerusi roda dan menterjemahkan maklumat ini ke dalam posisi relatif yang membolehkan kereta itu mengikuti kerusi roda. Terjemahan ini boleh dilakukan dalam rangkaian saraf. Walau bagaimanapun, data perlu dikumpulkan dengan memanipulasikan jarak kerusi roda dan troli antara 20cm hingga 69cm dan memanipulasi sudut kerusi roda dan troli antara -30 hingga 30 dengan had yang wujud bagi setiap kes. Nilai ujian MSE digunakan untuk menilai prestasi NN dan nilai pengesahan MSE digunakan untuk mencegah overfitting. ‘weight’ dan ‘bias’ yang dihasilkan melalui proses latihan bergantung kepada algoritma latihan, ‘weight’ awal dan ‘bias’awal dan data yang digunakan dalam proses. Algoritma latihan juga boleh berbeza-beza dengan set parameter yang berbeza, bilangan neuron yang berbeza dan fungsi pengaktifan yang berbeza. Set parameter yang digunakan dalam ‘traingd’ adalah ‘lr’, ‘max_fail’, ‘min_grad’, ‘goal’, ‘masa’, dan ‘epochs’. ‘weight’ dan ‘bias’ akhir dihasilkan dengan prestasi MSE minimum selepas beberapa percubaan digunakan untuk melatih NN dalam FPGA bersama dengan struktur NN yang diperoleh dalam Simulink. Pelaksanaan rangkaian saraf pada FPGA boleh dilakukan melalui konfigurasi perisian atau perkakasan. Walau bagaimanapun, litar operasi ‘floating-point’ perlu dibina untuk memastikan NN pada FPGA berfungsi. _______________________________________________________________________________________________________ The concern of the societies in creating a quality life for everyone without laying aside of the right of disable person leads to research on designing and fabricating autonomous robot. Wheelchair user usually faces the problem of carrying luggage along during travel as they need both of their hands to navigate their wheelchair. One of the solution for the problem is to create an Artificial Intelligent (AI) cart follower. Therefore, this research is to create an AI system for the AI cart follower with a visual based sensor. The visual based sensor gathered the information of the width, height, angle, x and y coordination of the colour pattern board which situated behind the wheelchair and translate this information into relative position information which enable the cart to follow the wheelchair. This translation can be done in neural network. However, the data needs to be collected in such a way that the output distance is manipulated between 20cm to 69cm and the output angle is manipulated between -30 to 30 with its restriction for each case. The test MSE value is used to evaluate the performance of NN and validation MSE value is used to prevent overfitting. The weights and biases generated through the training process is depended on the training algorithm, initial weights and biases for training and the dataset used in the process. The training algorithm may also vary with different sets of parameters, number of neurons and activation function. The set of parameters used in traingd are lr, max_fail, min_grad, goal, time, and epochs. The final weights and biases generated with the minimum MSE performance after several run is used to train NN in the FPGA together with the structure of NN obtained in Simulink. The implementation of neural network on the FPGA can be done through software or hardware configuration. However, the floating-point operation circuit needs to be built to ensure the NN on FPGA is functioning.
Contributor(s):
Tang Khai Luen - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007716
Language:
English
Subject Keywords:
societies; quality life; autonomous robot
First presented to the public:
6/1/2018
Original Publication Date:
8/10/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 124
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-08-14 14:51:13.895
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Embedded artificial intelligent (ai) To navigate cart follower1 2018-08-14 14:51:13.895