PENINGKATAN KINERJA SMARTRRT* DENGAN FASTRRT* UNTUK PERENCANAAN GLOBAL PATH PLANNING

SANJAYA, AGUNG (2026) PENINGKATAN KINERJA SMARTRRT* DENGAN FASTRRT* UNTUK PERENCANAAN GLOBAL PATH PLANNING. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) Cover.pdf Download (742kB) | Preview
	Text (BAB I) Bab 1.pdf Restricted to Registered users only Download (227kB)
	Text (BAB II) Bab 2.pdf Restricted to Registered users only Download (539kB)
	Text (BAB III) Bab 3.pdf Restricted to Registered users only Download (1MB)
	Text (BAB IV) Bab 4.pdf Restricted to Registered users only Download (681kB)
	Text (BAB V) Bab 5.pdf Restricted to Registered users only Download (215kB)
	Text (DAFTAR PUSTAKA) Daftar Pustaka.pdf Restricted to Registered users only Download (124kB)

Abstract

Path planning is a fundamental problem in autonomous robot navigation, particularly in environments with dense obstacles and narrow passages. The Rapidly-Exploring Random Tree Star (RRT*) algorithm is widely used due to its asymptotic optimality; however, its convergence speed is often limited by the use of uniform sampling. This research proposes the Fast–SmartRRT* method, which integrates fast sampling and smart sampling strategies to accelerate the discovery of an initial feasible path while improving the quality of the final path. The proposed method was evaluated through MATLAB-based simulations in two-dimensional (2D) static environments using three test scenarios with different levels of complexity, namely simple, moderate, and complex environments. The performance of RRT*, FastRRT*, SmartRRT*, and Fast–SmartRRT* was compared using three main metrics: the number of iterations required to find the initial path, computational time, and path length (path cost). Simulation results indicate that RRT* and SmartRRT* failed to reach the goal in moderate and complex environments within the maximum iteration limit due to inefficient exploration. FastRRT* successfully accelerated the discovery of the initial path but produced paths with relatively higher costs. In contrast, Fast–SmartRRT* consistently reached the goal in all test environments and achieved better path quality, with a reduction in path cost of approximately 1–1.5% compared to FastRRT* in complex environments, at the expense of higher computational time. These results demonstrate that Fast–SmartRRT* achieves a balance between exploration efficiency and path quality, particularly in high-complexity environments. Keywords: Path Planning, RRT*, Fast Sampling, Smart Sampling, Autonomous Robot Perencanaan jalur (path planning) merupakan permasalahan fundamental dalam navigasi robot otonom, terutama pada lingkungan dengan rintangan rapat dan narrow passage. Algoritma Rapidly-Exploring Random Tree Star (RRT*) banyak digunakan karena memiliki sifat optimalitas asimtotik, namun sering mengalami keterbatasan kecepatan konvergensi akibat mekanisme uniform sampling. Penelitian ini mengusulkan metode Fast–SmartRRT* sebagai penggabungan strategi fast sampling dan smart sampling untuk mempercepat penemuan jalur awal sekaligus meningkatkan kualitas jalur akhir. Evaluasi dilakukan melalui simulasi MATLAB pada lingkungan dua dimensi (2D) dengan rintangan statis menggunakan tiga skenario lingkungan uji, yaitu lingkungan mudah, sedang, dan kompleks. Kinerja metode RRT*, FastRRT*, SmartRRT*, dan Fast–SmartRRT* dibandingkan berdasarkan tiga metrik utama, yaitu iterasi ditemukannya jalur awal, waktu komputasi, dan panjang jalur (path cost). Hasil simulasi menunjukkan bahwa RRT* dan SmartRRT* tidak mampu mencapai tujuan pada lingkungan sedang dan kompleks hingga batas iterasi maksimum. FastRRT* berhasil menemukan jalur awal lebih cepat, namun menghasilkan kualitas jalur yang relatif lebih tinggi (path cost lebih besar). Sebaliknya, Fast–SmartRRT* mampu mencapai tujuan secara konsisten pada seluruh lingkungan uji dan menghasilkan kualitas jalur yang lebih baik, dengan penurunan path cost hingga sekitar 1–1,5% dibandingkan FastRRT* pada lingkungan kompleks, meskipun memerlukan waktu komputasi yang lebih besar. Hasil ini menunjukkan bahwa Fast–SmartRRT* mampu mencapai keseimbangan antara kecepatan eksplorasi dan kualitas lintasan, khususnya pada lingkungan dengan tingkat kompleksitas tinggi. Kata Kunci: Path Planning, RRT*, Fast Sampling, Smart Sampling, Robot Otonom

Item Type:	Thesis (S1)
NIM/NIDN Creators:	41421110020
Uncontrolled Keywords:	Path Planning, RRT*, Fast Sampling, Smart Sampling, Robot Otonom
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.31 Machine Learning/Pembelajaran Mesin 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.32 Neural Nets (Neural Network)/Jaringan Saraf Buatan 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn
Divisions:	Fakultas Teknik > Teknik Elektro
Depositing User:	khalimah
Date Deposited:	19 Feb 2026 01:26
Last Modified:	19 Feb 2026 01:26
URI:	http://repository.mercubuana.ac.id/id/eprint/100978

Actions (login required)

View Item