Claim Missing Document
Check
Articles

Found 3 Documents
Search

Inverse kinematic solution and singularity avoidance using a deep deterministic policy gradient approach Surriani, Atikah; Wahyunggoro, Oyas; Imam Cahyadi, Adha
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp2999-3009

Abstract

The robotic arm emerges as a subject of paramount significance within the industrial landscape, particularly in addressing the complexities of its kinematics. A significant research challenge lies in resolving the inverse kinematics of multiple degree of freedom (M-DOF) robotic arms. The inverse kinematics of M-DOF robotic arms pose a challenging problem to resolve, thus it involves consideration of singularities which affect the arm robot movement. This study aims a novel approach utilizing deep reinforcement learning (DRL) to tackle the inverse kinematic problem of the 6-DOF PUMA manipulator as a representative case within the M-DOF manipulator. The research employs Jacobian matrix for the kinematics system that can solve the singularity, and deep deterministic policy gradient (DDPG) as the kinematics solver. This chosen technique offers enhancing speed and ensuring stability. The results of inverse kinematic solution using DDPG were experimentally validated on a 6-DOF PUMA arm robot. The DDPG successfully solves inverse kinematic solution and avoids the singularity with 1,000 episodes and yielding a commendable total reward of 1,018.
Discount Factor Parametrization for Deep Reinforcement Learning for Inverted Pendulum Swing-up Control Surriani, Atikah; Maghfiroh, Hari; Wahyunggoro, Oyas; Cahyadi, Adha Imam; Fajrin, Hanifah Rahmi
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i1.10268

Abstract

This study explores the application of deep reinforcement learning (DRL) to solve the control problem of a single swing-up inverted pendulum. The primary focus is on investigating the impact of discount factor parameterization within the DRL framework. Specifically, the Deep Deterministic Policy Gradient (DDPG) algorithm is employed due to its effectiveness in handling continuous action spaces. A range of discount factor values is tested to evaluate their influence on training performance and stability. The results indicate that a discount factor of 0.99 yields the best overall performance, enabling the DDPG agent to successfully learn a stable swing-up strategy and maximize cumulative rewards. These findings highlight the critical role of the discount factor in DRL-based control systems and offer insights for optimizing learning performance in similar nonlinear control problems.
Design of a Monitoring and Nutrient Management System Based on Internet of Things (IoT) for Hydroponic Method Using MIT App Inventor Priawardana, Shandy Gilang; Surriani, Atikah
Jurnal Listrik, Instrumentasi, dan Elektronika Terapan Vol 6, No 1 (2025)
Publisher : Departemen Teknik Elektro dan Informatika Sekolah Vokasi UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/juliet.v6i1.99431

Abstract

Hydroponics is an agricultural method that uses a growing medium with low nutrient content. In hydroponics, nutrients are required. These nutrients are very important for plant growth in hydroponics. If hydroponic plants lack nutrients, they will die. Water needs in hydroponic reservoirs also need to be considered, so that the water in hydroponics remains stable. Other factors such as water temperature are also important in the hydroponic method. High temperatures can inhibit plant growth and can cause plants to grow faster (bolting). Therefore, the design of temperature monitoring, as well as nutrient management and water level in hydroponic reservoirs based on the Internet of Things (IoT) is made. This tool can manage hydroponic systems efficiently and is easy to operate because it is IoT-based, so that farmers can monitor and manage only via Smartphone on the MIT App Inventor application. This research method has several important stages, namely analysis of the needs of tools and materials, tool design, functional testing of tools, and data analysis. The system will measure the value of nutrients, water temperature, and water level. From this data, it will be processed and arranged for monitoring and management in hydroponic. The results of this final project are the average TDS sensor error of 3.9232%, the average HC-SR04 ultrasonic sensor error of 3.53%, the average DS18B20 temperature sensor error of 2.7513%. This tool can perform monitoring and nutrient management in IoT-integrated hydroponics well, because the resulting error is below 5% and the system runs well.