Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electronics and Instrumentation Systems Buletin Ilmiah Sarjana Teknik Elektro Journal of Robotics and Control (JRC) Control Systems and Optimization Letters
Gilang Nugraha Putu Pratama
Unknown Affiliation
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Mechanical Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Implementasi Kendali Logika Fuzzypada Robot Line Follower Gilang Nugraha Putu Pratama; Andi Dharmawan; Catur Atmaji
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 4, No 1 (2014): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (755.367 KB) | DOI: 10.22146/ijeis.4221

Abstract

Robot line follower merupakan robot otonom yang dapat mengikuti jalur. Jalurnya bisa berupa garis berwarna hitam diatas permukaan putih atau sebaliknya. Pada penelitian ini, robot line follower menggunakan sistem kendali logika fuzzy dengan metode Mamdani. Selama ini robot line follower kebanyakan dirancang untuk jalur dengan lebar yang tetap, namun dengan sistem kendali logika fuzzy ini dapat mengenali jalur dengan variasi lebar antara satu hingga delapan titik sensor. Robot line follower ini mengimplementasikan 18 aturan fuzzy untuk memetakan antara antecedent posisi dan lebar jalur, dengan consequent kecepatan laju robot. Aturan fuzzy terdiri dari masing-masing 9 aturan untuk kondisi jalur tunggal dan jalur percabangan dua jalur. Robot line follower ini mampu menganalisis 57 case jalur dengan kendali fuzzy, mulai dari lebar jalur 2 hingga 12 cm. Dimana 36 case analisis jalur tunggal dan 21 casejalur percabangan dua jalur. Robot line follower ini juga mampu menyesuaikan kecepatan laju sesuai lebar jalurnya. Kata kunci— kendali logika fuzzy, kendali Mamdani, robot line follower Line follower Robot is an autonomous robot that can follow a track. The track can be a black line on a white surface or vice versa. In this study, the line follower robot using fuzzy logic control system by the method of Mamdani. Mostly line follower robots are designed with a fixed width, but with fuzzy logic control system itcan recognize the wide variation between one to eight pointsof sensor. This line follower robot implements18 fuzzy rules to map between the antecedents position and width of the line, with a consequents speed rate of the robot. There are 9 rules each  for single line and two routes branching paths. This line follower robot is designedwith capabilityto analyze 57 cases, the width of the line from 2 to 12 cm. There are 36 casesof analysis on a single line and 21 cases on two lines branching paths. This line follower robot can adjust it’s speed depend on the wide of the track. Keywords— fuzzy logic controller, Mamdani-controller, line follower robot
Enhance Deep Reinforcement Learning with Denoising Autoencoder for Self-Driving Mobile Robot Pratama, Gilang Nugraha Putu; Hidayatulloh, Indra; Surjono, Herman Dwi; Sukardiyono, Totok
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21713

Abstract

Over the past years, self-driving mobile robots have captured the interest of researchers, prompting exploration into their multifaceted implementation. They have the potential to revolutionize transportation by mitigating human error and reducing traffic accidents. The process of deploying self-driving mobile robots can be divided into several steps, such as algorithm design, simulation, and real-world application. This research paper presents a simulation using DonkeyCar on the Mini Monaco track, employing a Soft Actor-Critic (SAC) alongside a denoising autoencoder. At this point, it is limited to the simulation, serving as a proof of concept for further research with hardware implementation. The simulation verifies that relying solely on SAC for the convergence of policy is not sufficient; it yields a mean episode length of only 28.82 steps and a mean episode reward of 0.7815. The simulation ended after 3557 steps due to the inability of SAC alone to converge, without completing a single lap. Later, by integrating the denoising autoencoder, convergence of policy can be achieved. It enables DonkeyCar to adeptly track the lane of the circuit. The denoising autoencoder plays an important role in accelerating the convergence of transfer learning. Notably, the mean reward per episode reached 2380.4387, with an average episode length of 771.71 and a total of 114357 steps taken. DonkeyCar manages to complete several laps. These results affirm the effectiveness of SAC with a denoising autoencoder in enhancing the performance of self-driving mobile robots.
Benchmark Analysis of Sampling Methods for RRT Path Planning Pratama, Gilang Nugraha Putu; Dhewa, Oktaf Agni; Priambodo, Ardy Seto; Baktiar, Faris Yusuf; Prasetyo, Rizky Hidayat; Jati, Mentari Putri; Hidayatulloh, Indra
Control Systems and Optimization Letters Vol 2, No 2 (2024)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/csol.v2i2.132

Abstract

Path planning is a crucial aspect of mobile robot navigation, ensuring that robots can safely travel from their initial position to the goal. In real-world applications, path planning is essential for autonomous vehicles, drones, warehouse robots, and rescue robots to navigate complex environments efficiently and safely. One effective method for path planning is the Rapidly-exploring Random Tree (RRT) algorithm, which is particularly practical in maze-like environments. The performance of RRT depends on the sampling methods used to explore the maze. Sampling methods are important because they determine how the algorithm explores the search space, affecting the efficiency and success of finding an optimal path. Poor sampling can lead to suboptimal or infeasible paths. In this study, we investigate different sampling strategies for RRT, specifically focusing on uniform sampling, Gaussian sampling, and the Motion Planning Network (MPNet) sampling. MPNet leverages a neural network trained on past environments, allowing it to predict promising regions of the search space quickly, unlike traditional methods like RRT that rely on random exploration without prior knowledge. This makes MPNet much faster and more efficient, especially in complex or high-dimensional spaces. Through a benchmarking analysis, we compare these methods in terms of their effectiveness in generating feasible paths. The results indicate that while all three methods are effective, MPNet sampling outperforms uniform and Gaussian sampling, particularly in terms of path length. The mean path length generated, based on a sample size of 30, is 13.115 meters for MPNet, which is shorter compared to uniform and Gaussian sampling, which are 18.27 meters and 18.088 meters, respectively. These findings highlight the potential to enhance path planning algorithms using learning-based sampling methods.
Exploring RRT and BiRRT Algorithms: A Review and Simulation-Based Comparison for Fixed-Wing UAV Path Planning Pratama, Gilang Nugraha Putu; Dhewa, Oktaf Agni; Jati, Mentari Putri; Hidayatulloh, Indra; Gunawan, Teddy Surya; Gunawan, Syaiful Ardy
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 2 (2026): April
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i2.14511

Abstract

Path planning plays a vital role in ensuring the safe and efficient navigation of fixed-wing unmanned aerial vehicles (UAVs), particularly in cluttered and complex environments. The increasing demand for autonomous UAV operations highlights the need for reliable algorithms capable of generating optimal and collision-free trajectories. This study addresses the challenge by reviewing recent uses of the Rapidly-exploring Random Tree (RRT) algorithm in various robotic platforms and navigation tasks. The research contribution of this paper is a comparative analysis of RRT and BiRRT for fixed-wing UAV path planning, quantifying trade-offs between path length, computation time, and obstacle clearance using a real-world 2D urban map. This addresses a gap in the literature, as few studies have directly compared these algorithms specifically for fixed-wing UAV surveillance missions. The methods involve implementing both RRT and BiRRT in a simulated environment where each algorithm is evaluated over 100 runs to measure performance metrics such as path length, computation time, and obstacle clearance. A realistic urban map is used to test the algorithms under consistent starting and goal positions. The results show that both RRT and BiRRT achieve a 100% success rate in finding collision-free paths. BiRRT consistently generates shorter paths and requires less computation time, making it more suitable for time-sensitive missions. However, RRT produces safer trajectories with greater average clearance from obstacles, which is advantageous in environments with high collision risk. The findings demonstrate a clear trade-off between safety and efficiency. In conclusion, BiRRT is recommended for missions where speed and efficiency are prioritized, while RRT is better suited for operations emphasizing safety and obstacle avoidance.
Co-Authors Andi Dharmawan Ardy Seto Priambodo Catur Atmaji Faris Yusuf Baktiar Gunawan, Syaiful Ardy Herman Dwi Surjono Indra Hidayatulloh Mentari Putri Jati Oktaf Agni Dhewa Rizky Hidayat Prasetyo Teddy Surya Gunawan Totok Sukardiyono