Improved PSO Berbasis Current-Aware Dengan Predictive Collision Avoidance Untuk Dynamic Path Planning Pada Unmanned Surface Vehicle

Syeichu, Muhammad Mukhlis (2026) Improved PSO Berbasis Current-Aware Dengan Predictive Collision Avoidance Untuk Dynamic Path Planning Pada Unmanned Surface Vehicle. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6022211024-Master_Thesis.pdf Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Perencanaan jalur adalah komponen penting pada navigasi otonom USV untuk menghasilkan lintasan yang aman, efisien, dan bebas tabrakan di lingkungan maritim yang dipengaruhi rintangan statis, rintangan dinamis, dan arus laut. Penelitian ini mengusulkan kerangka kerja berbasis Improved Particle Swarm Optimization (IPSO) dengan representasi waypoint dan fungsi objektif yang mempertimbangkan waktu tempuh, panjang lintasan, konsumsi energi, keselamatan, dan kelancaran. Simulasi dilakukan pada area dua dimensi yang memuat rintangan statis, rintangan dinamis, arus konstan, dan arus spasio temporal. Untuk meningkatkan keselamatan, diterapkan Predictive Collision Avoidance (PCA) yang memprediksi posisi USV dan rintangan, lintasan divalidasi secara closed loop menggunakan LOS dan pengendali heading PID. Kontribusi utama meliputi perencanaan berbasis waktu tempuh, pemodelan arus spasio temporal, pemodelan rintangan dinamis ruang waktu, mekanisme penghindaran prediktif, strategi optimasi energi waktu, dan validasi closed loop. Hasil diharapkan memperkuat adaptivitas, keselamatan, dan efisiensi sistem navigasi otonom USV =================================================================================================================================
Path planning is a critical component of autonomous USV navigation for generating safe, efficient, and collision-free trajectories in maritime environments influenced by static obstacles, dynamic obstacles, and ocean currents. This study proposes an Improved Particle Swarm Optimization (IPSO)-based framework employing waypoint representation and an objective cost function that incorporates travel time, path length, energy consumption, safety, and path smoothness. Simulations are conducted in a two-dimensional operational environment containing static obstacles, dynamic obstacles, constant currents, and spatio-temporal currents. To enhance navigational safety, a Predictive Collision Avoidance (PCA) mechanism is implemented to predict the future positions of both the USV and surrounding obstacles, while the planned trajectories are validated through a closed-loop framework utilizing Line-of-Sight (LOS) guidance and a PID heading controller. The main contributions of this work include travel-time-oriented path planning, spatio-temporal current modeling, space-time dynamic obstacle modeling, a predictive collision avoidance mechanism, an energy–time optimization strategy, and closed-loop validation. The proposed approach is expected to improve the adaptability, safety, and efficiency of autonomous USV navigation systems.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Unmanned Surface Vehicle, Improved Particle Swarm Optimization, Path Planning, Predictive Collision Avoidance, Spatio-Temporal Ocean Current, LOS Guidance, PID Controller, Closed-Loop Navigation
Subjects:	T Technology > T Technology (General) T Technology > TE Highway engineering. Roads and pavements T Technology > TE Highway engineering. Roads and pavements > TE228.3 Intelligent transportation systems.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User:	Muhammad Mukhlis Syeichu
Date Deposited:	05 Aug 2026 02:51
Last Modified:	05 Aug 2026 02:51
URI:	http://repository.its.ac.id/id/eprint/143847

Actions (login required)

View Item