Integrasi MPC Dengan Sistem Deteksi Lajur dan Kendaraan Untuk Mengikuti Lajur dan Penjagaan Jarak Aman Berkendara Pada Mobil Otonom

Aufar, Muhammad Ayub Purnama (2023) Integrasi MPC Dengan Sistem Deteksi Lajur dan Kendaraan Untuk Mengikuti Lajur dan Penjagaan Jarak Aman Berkendara Pada Mobil Otonom. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07111940000190-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (3MB) | Request a copy

Abstract

Penelitian ini mengeksplorasi integrasi deteksi lajur dan kendaraan dalam mobil otonom menggunakan Model Predictive Control (MPC) dengan sensor ultrasonic, lidar, radar, dan kamera. Fokusnya pada konsep driving scene understanding, terutama deteksi jarak terhadap objek, yang kritis untuk pengambilan keputusan aman. MPC, sebagai kontroler efektif, memanfaatkan pergerakan lateral dan longitudinal untuk menjaga kendaraan pada jalur yang ditentukan. Tujuannya adalah menciptakan mobil otonom responsif dan dapat diandalkan. Pengujian mencakup variasi kondisi lingkungan, dan sistem deteksi lajur terbukti efektif, tetapi menghadapi tantangan saat sudut lajur tak terdeteksi. Deteksi kendaraan cukup akurat, tetapi dipengaruhi oleh kecerahan lingkungan virtual dan akurasi model ACF yang terbatas. MPC mampu merespons hasil deteksi, meskipun hasil pengujian menunjukkan perbedaan dengan penelitian sebelumnya, dengan peningkatan error pada RMSE posisi X dan peningkatan kinerja pada RMSE posisi Y. Dengan demikian, penelitian ini menyajikan solusi terintegrasi untuk meningkatkan kemampuan kendaraan otonom dalam memahami dan merespons lingkungan sekitar.
=================================================================================================================================
This research explores the integration of lane and vehicle detection in autonomous vehicles using Model Predictive Control (MPC) with ultrasonic, lidar, radar, and camera sensors. The focus is on the concept of driving scene understanding, particularly object distance detection, crucial for safe decision-making. MPC, as an effective controller, utilizes lateral and longitudinal movements to keep the vehicle on the designated path. The goal is to create a responsive and reliable autonomous vehicle. Testing involves various environmental conditions, and the lane detection system proves effective but faces challenges when lane angles are undetected. Vehicle detection is fairly accurate, yet influenced by the brightness of the virtual environment and limited accuracy of the ACF model. MPC can respond to detection results, although test outcomes differ from previous studies, showing increased error in X-axis position RMSE and improved performance in Y-axis position RMSE. Thus, this research presents an integrated solution to enhance the capabilities of autonomous vehicles in understanding and responding to their surrounding environment.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Autonomous Vehicles, Detection Integration, Driving Scene Understanding, Model Predictive Control (MPC), Transportation Technology, Driving Scene Understanding, Integrasi Deteksi, Kendaraan Otonom, Teknologi Transportasi
Subjects:	T Technology > T Technology (General) > T385 Visualization--Technique T Technology > T Technology (General) > T57.62 Simulation T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > TA Engineering (General). Civil engineering (General) > TA1573 Detectors. Sensors T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	Muhammad Ayub Purnama Aufar
Date Deposited:	05 Feb 2024 17:38
Last Modified:	05 Feb 2024 17:38
URI:	http://repository.its.ac.id/id/eprint/106131

Actions (login required)

View Item