Emotion is an intense feeling that is directed at someone or something that can trigger to take an action or expression from inside or outside themself. In everyday life, it is important to be able to understand and predict the emotional state of a person. One of the emotions of a person can be known through facial expressions, but sometimes a person can manipulate it by controlling his facial expressions. Therefore, we need a system that can predict children's emotions based on changes in their body condition. In this study, two sensors were used, namely the GSR sensor and the heart rate sensor. The data obtained from each sensor is processed using a microcomputer or raspberry pi. Furthermore, the sensor output will be processed first using the Support Vector Machine (SVM) method by comparing 2 pieces of data, namely normalized data and unnormalized data based on linear, polynomial, RBF, and sigmoid kernels, so that a model will be obtained and will be used as a reference to predict 3 types of emotions namely happy, sad, and angry. From this research, the best model is obtained when using linear and sigmoid kernels with normalized data types. This is proven when using normalized data with linear and sigmoid kernels, there are only 18 incorrect data with an accuracy rate of 86.67%. This research is expected to help parents and teachers to predict emotions, especially in children.

Many researchers have developed disaster robots. This paper aims to create disaster robot assistant for helping humans in handling victims of natural disasters. This preliminary research is devoted to the interface and instrumentation of the Brushless Direct Current (BLDC) motor. The focus of this paper is on programming techniques for BLDC motors based on Arduino and Digital to Analog Converter (DAC) which are open loop. The robot used to monitor areas that are declared dangerous and can cause natural disasters. In this preliminary research, an assist robot was created that runs on roads that are not intended to help humans carry several environmental monitoring devices on volcanoes. The robot carries an Unmanned Aircraft Vehicle (UAV) equipped with several sensors for monitoring environmental conditions. System testing is to provide setpoint data and take measurements of the response in the form of output voltage from the DAC and motor rotation speed (RPM). The measurement results for motor speed (RPM) is 11.915 and for DAC (volt) is 0.0169, where the data is a direct comparison of measurements to measurements from settings using Arduino.

Lately, during the COVID-19 pandemic, hospitals experienced an increase in the number of patients due to the rapid spread of the virus. The need for services in hospitals has increased compared to normal days. Therefore Healthcare Robot is needed that can help the service of patients and medical personnel in the hospital. The robot must be able to detect and recognize existing objects and put them in the expected place. The sensor itself here uses a camera depth or stereo camera. The input results are in the form of RGB-D Image, which we then convert to point cloud to get 3D information. Then the 3D information will be segmented and clustered to get the object to be detected using a RANSAC and Euclidean Cluster. Then feature extraction uses the Viewpoint Features Histogram (VFH) descriptor to get the characteristics of the object. Then the matching with the dataset using the Artificial Neural Network continued with Labelling and visualization of the result. With this system, the robot can detect and recognize objects around the hospital so that the robot can take action on these objects. At the end of this project, nine datasets and three scenes resulting from capture by the writer were tested. The results show an average accuracy of 90.77% for testing three multi-object scenes and 98.73% for testing one object.

The robot contest is one of the fascinating events that drive innovation in robotics research and development. ERISA is a humanoid robot dancing developed by EEPIS students to participate in such a contest. ERISA robot is designed to be able to dance traditional Indonesian dances with agile and attractive movements. ERISA robot has a mission to dance and move from the Start Zone to the Finish Zone. Unfortunately, it is hard to make the ERISA robot stop at the desired zone without rigorous tuning because the walking trajectory in ERISA still uses an open-loop control. Since each field zone in the game field has a different color characteristic, it can be used as the robot’s guidance to assist its walking trajectory. In this research, the Pixy CMUcam5 camera will detect the Finish Zone in the game field and marked it as the target position. Since the robot heading is changing during its movement, an Inertial Measurement Unit (IMU) sensor is used to correct the projection of the target position. Thus, the location is processed in the form of(X, Y) coordinates, which are used as the reference to control the robot walking trajectory. As a result, the robot can walk towards the target accurately.

A robot guide is a robot that is used to guide users from a place of origin to their destination. During carrying out the guiding task, the robot must ensure that the user always follows wherever the direction is headed by the robot until it reaches the destination location. To get this certainty, one of the things that must be considered is the direction the user must walk in the direction of the robot's movement. In this paper, we built a system to monitor user awareness levels to coordinate with robots. We use RGB-D data from the Kinect sensor to detect target partners, their position, and orientation. The level of awareness is calculated using the Social Force Model (SFM) based on the target partner's position and body orientation parameters. This level of awareness will be used by the robot to evaluate the appropriate actions according to the target partner's activities. Based on the results of experiments, the level of awareness of target partners can be calculated and transformed in the form of attractive or repulsive forces towards robots.

In general, a socially-aware mobile robot must have an ability to safely navigate among human environment. To address with this competency, the mobile robots must be able to detect the existence of humans around. This paper proposes the use of Fast Fourier Transform (FFT) to analyze shape-models of human legs that is obtained from Laser Range Finder (LRF) scanning results. A 240° of LRF was used to capture and visualize the environment in one dimensional plane. The plane is then converted into one dimensional signal that consists of 1,024 data points. These data points represented the distance of all measured points. A specific set of points formed the pattern of human legs only is then resized into 32 data. This resized-data is transformed into frequency by using FFT. The result of FFT is then fed into Support Vector Machine (SVM) to be classified into two classes, they are human or not human. Based on the experimental results, our proposed method shows a promising result in order to detect human based on one dimensional feature of his legs by achieving more than 80% of accuracy.

One of the keys to the success of interaction between people is communication. Communication can be done verbally or non-verbally. In this paper, we build interactions between humans and computers using hand gestures. The hand gesture is recognized by the palm of the hand which is obtained from the results of human skeleton segmentation through camera Kinect. Recognition of palm gestures is performed on a series of RGB Kinect output frames. Histogram of Oriented Gradient (HOG) is used to produce a palm frame per frame gesture feature which is arranged in 4 seconds as a gesture descriptor. Dynamic Time Warping (DTW) is used as a classifier that will compare the description of the input gesture with the template gesture description. Based on the results of the experiment, the performance of the hand gesture recognition system reached 76.7%.

Remotely operated vehicle (ROV) plays an important role in the exploration of underwater objects for observation of marine life, oil and gas exploration and rescue. In underwater diving, a variety of factors can influence the movements carried out by ROV such as water flow, water waves, water pressure, etc. Control of balance and depth in the ROV are important factor in carrying out various missions ROV found it in the form of water flow and water waves. PID controller is still ineffective due to the nonlinear nature of the ROV and therefore this paper proposes to add a Fuzzy logic controller to deal with the nonlinearity in the ROV. With a combination of PID and Fuzzy controller, the ROV is able to balance while making the diving and maneuvering moves despite receiving interference in the water. Using the proposed controller, the ROV is able to respond well with respect to disturbances in attitudes and depth motion control scenarios.

Legged robot has an increasing attention from researchers in this recent year in the form of humanoid or animaloid robot. One of the animaloid robot type is quadruped. this paper will discuss about crawling gait planning that will be proposed on a Quadruped robot. This gait is expected to be able to maintain the balance of the robot pitch and roll angle movement when walking. The trajectory planning used in this case is linear translation and sinusoidal shaped gait trajectory. In this study, there are no obstacles and just walk on a flat terrain. This study focuses on the gait trajectory generation and timing adjustment to minimize the rolling and pitching movement of the robot while walking. This study will not only show the simulation, but also the implementation results of the crawling-gait planning to the robot.

Utilization of wireless sensor network technology can improve the anticipation of the occurrence of fire hazards in the smart home; this is done by replacing the human task in monitoring the situation around the home by using multiple sensors which can directly interact with the environment. The goal of this paper is building the early fire detection systems on smart home-based wireless sensor network monitoring. Sensors are used to detect the level of fire danger include temperature sensors, humidity, carbon monoxide, and smoke. The system use fuzzy logic inference systems to process the data from the four sensors in order to improve the reliability and accuracy of the information provided for the system that will give warning to users. Based on the results obtained, the system has been able to give an alarm warning to users appropriately. The proposed system also implement sleep scheduling method in the system which can improve the delivery efficiency of data packets and can reduce battery resource usage.

T-FLoW (Teen FLoW) is one of the teen size humanoid robots developed by ER2C (EEPIS Robotics Research Center) laboratory. There are various problems that occur when the robot performs dynamic locomotion, one of them is the overloading received on every actuator thus causing the asynchronous locomotion of the robot. In this paper, the goal to be achieved is making a vertical jumping mechanism of the robot to become more synchronized. Therefore, multivariable control will be used as a method to distribute overload for each actuator on the same joint so that actuator can be more synchronized. Finally, multivariable control has a positive effect in which the success rate of the vertical jumping mechanism is about 80%, and the robot managed to hover on the air for about 7-9 ms.

Particle Swarm Optimization (PSO) is fast and popular algorithm to find the optimum value of non-linear and multi-dimensional function. However, it often easily trapped into local optima because the particles move closer to the best particle quickly. This paper purposes a new algorithm called Multi-Group Particle Swarm Optimization with Random Redistribution (MGRR-PSO) that tried to solve the weakness of standard PSO. MGRR-PSO combines two groups of PSO with opposite acceleration coefficients. In addition, some particles are redistributed when they are trapped in local optima. Experimental studies on 5 benchmark functions with 50-dimensions and 100-dimensions show that the MGRR-PSO can solve the problems that can't be solved by original PSO with better performance.

The Inverted pendulum platform is an example of classic unstable control system. Even though the system has been fairly tested and documented, it still draws attention of many researchers due to its application in unicycle robot. In the unicycle robot, there are problems that arise control strategy in the reading position of the robot tilt. This paper proposes to use the Kalman Filter Estimation angle for data processing Inertial Measurement Unit (IMU) to obtain estimates of the robot tilt position. In the previous study also found problems when using only one relatively low speed IMU sensor obstacles that the response given by the sensor. This paper uses two IMU sensor readings to speedup the response of the sensor and get accurate data during a shorter period. The proposed algorithm uses a new sensor placement strategy on a rigid body robot, with a reading sensor in interleaved mode. Kalman Filter algorithm incorporating placement constraints to achieve the estimated position of the robot tilt angle accurately. The results show synchronization time sampling of the two Inertial Measurement Unit (IMU) sensor improves the response and a twice faster in estimating the position of the robot tilt compared to the use of one sensor. Merging time sampling 2 sensors can be applied on a unicycle robot in order to have a quick response to the reading of the tilt position of the robot.

This paper presents neuro-based push recovery controller applied in humanoid biped robot in order to keep the stability with minimum energy required. There are three motion patterns in human behavior when it gets external perturbation, those are ankle behavior, hip behavior, and step behavior. We propose the new model of modular recurrent neural network (MRNN) for performing online learning system in each motion behavior. MRNN consists of several recurrent neural networks (RNNs) working alternately depending on the condition. MRNN performs online learning process of each motion behavior controller independently. The aim of push recovery controller is to manage the motion behavior controller by minimizing the energy required for responding to the external perturbation. This controller selects the appropriate motion behavior and adjusts the gain that represent the influence of the motion behavior to certain push disturbance based on behavior graphs which is generated by adaptive regression spline. We applied the proposed controller to the humanoid robot that has small footprint in open dynamic engines (ODE). Experimental result shows the effectiveness of the push controller stabilizing the external perturbation with minimum energy required.

One of the focus in humanoid robot research is head motion and mechanism, yet it still has a limited pan and tilt motion to represent a real human head movement. This study is working on kinematic analysis of an earlier proposed 7 DOF manipulator system that can closely mimics a human head motion capability. The concentration of the work is to design a head mechanism and to develop a composite kinematics model of the head motions which includes the eyes, the head itself and the neck. Such a model was also simulated using the dynamic V-REP application to verify its movements capabilities and to compare the kinematics analysis. Stages will be discussed in more detail in the chapter on testing. The results showed transformation biggest difference is 2.3340% error that occurred on 3 DOF motion contained in the head manipulator.