Skripsi

PENGGUNAAN CONVOLUTIONAL NEURAL NETWORK UNTUK CONTROL STEERING PADA AUTONOMOUS VEHICLE

---

Penilaian

---

Autonomous Vehicle is a form of technology in vehicles that allows forcontrolling the auto pilot system using artificial intelligence. The basic technologypossessed by Autonomous Vehicle consists of four basic technologies, namelymotion control, modeling, map building and path planning. Motion controlfunctions to control the direction of movement in a vehicle, which in this case is thesteering control. Research on steering control was carried out using variousmethods. However, there are veryfew studies that discuss autonomous steeringcontrol, use secondary data, and are limited by the low level of test performance.Therefore, this study will overcome this problem by using the convolutional neuralnetwork (CNN) method. The data used are primary data in the form of 1011 imagesfrom street videos at the Faculty of Engineering, Sriwijaya University. The resultsof this study indicate that the convolutional neural network has been able to controlthe steering direction of an autonomous vehicle byusing a self-made modelarchitecture design and has good performance with a small error rate (MSE) of71.76. These results indicate that the design model architecture itself has betterperformance in the steering control process in an autonomous vehicle.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2007001400	T39721	T397212020	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T397212020

Publisher

Inderalaya : Jurusan Teknik Elektro, Fakultas Teknik Universitas Sriwijaya., 2020

Collation

xviii, 109 hlm. : ilus. ; 28 cm

Language

Indonesia

ISBN/ISSN

-

Classification

621.381 07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Elektro
Control Steering-Autonomous Vehicle

Specific Detail Info

-

Statement of Responsibility

DS

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment