Edison A. Roxas

Obstacle avoidance of hybrid mobile-quadrotor vehicle with range sensors using fuzzy logic control

This study presents a fuzzy logic based approach to a hybrid mobile quadrotor vehicle that is able to perform goal seeking and obstacle avoidance, given that the obstacles are nonmoving and are along a fixed path. Two range sensors will be used to construct the input variable of the fuzzy logic control. The algorithms are developed to achieve goal position while avoiding obstacles. Simulations are conducted and the efficiency of the results using the method is proved using MATLAB.

Recognition of handwritten alphanumeric characters using Projection Histogram and Support Vector Machine

The study investigates the accuracy and precision of the proposed system by cross examining the values solved using the proposed system with the values solved manually. Since the feature extractor and classifier directly influences the accuracy and precision of Optical Character Recognition, the study considered choosing the top of the line combination of Feature Extractor-Classifier combination for handwritten characters which is the Projection Histogram and Support Vector Machine (SVM) combination. For this study, the accuracy of this system is presented in terms of character recognition performance where alphanumeric characters (62 characters in total) are to be tested.

A multiple level MIMO fuzzy logic based intelligence for multiple agent cooperative robot system

Fuzzy Logic is a many valued logic and it is very similar to human reasoning which is not binary. It uses approximate measures rather than exact, making it suitable for linguistic variable and analysis. It has been applied to many applications in artificial intelligence, control and robotics. In this paper, the authors develop an artificial intelligence using multiple fuzzy logic for a dynamic multiple agent robot system. The system is made up of multiple robots with multiple identity assignment; which means that each robot will have its distinct behavior. In order to design pure fuzzy logic artificial intelligence, we used fuzzy logic block in different parallel and series configuration making giving it multiple fuzzy logic levels. Furthermore, there is multiple input - multiple output (MIMO) fuzzy logic implementation in one of our several fuzzy logic blocks, this is necessary in order to utilize pure fuzzy logic control in the whole artificial intelligence. The multi agent cooperative robot platform we choose to test our artificial intelligence is a multiple robot system for FIRA Micro-Robot World Soccer Tournament (MiroSot). In our setup, there are three robots to be assigned dynamically with three different identities; the Forward, the Back and the Goal-keeper. Robot identity assignment depends on the position of each robot with respect to the position of the ball. To tune each fuzzy logic block individually isolation is done. Some tuning procedures are performed in a simulator while most of them are tuned in the actual platform. Although tuning procedures are rigorous, the linguistic approach and human reasoning nature of fuzzy logic made it possible to achieve its completion. Overall, the proposed artificial intelligence produced favorable response based on the expected outcome and experimentations.

Development of a DC-DC converter with Current Mode Control for multi-source renewable energy harvesting system

This paper presents a multiple input energy harvesting system that addresses the intermittency of renewable energy sources which outputs a regulated voltage using a boost converter which makes use of the Current Mode Control technique (CMC). Photovoltaic cell exposed to both artificial and natural light, and piezoelectric transducers mechanically excited by vibrations produced using a function generator-powered speaker are used as the energy sources in conducting the experimentation. A scalability analysis for both the piezoelectric and solar cells are done, as well as regulation tests of output voltage for the boost converter in lieu of varying load and line voltages are executed. A step test of various input voltages for the boost converter and determining the load resistance value where the system is most efficient are also done. Comparison of the performance of DC-DC converters with and without CMC is also conducted.

Analysis of traffic information dissemination using vehicular ad hoc network simulations

In the Philippines, the Metropolitan Manila Development Authority (MMDA) uses closed-circuit television (CCTV) to manually monitor and analyze traffic situations. However, this solution is tedious and limited to manpower resources. A possible method that can be used to analyze traffic siutations is through the use of vehicular ad hoc network (VANET) simulations. A VANET is a network consisting of moving vehicles as nodes. This network can be used as a medium for information dissemination. Two important factors in VANETs are routing protocols which allow mobile nodes to exchange data from each other and mobility models which represent the behavior and movement of the mobile nodes. This paper focuses on using VANET simulation to recreate traffic scenarios in Manila, Philippines and to determine the most efficient combination of mobility model and routing protocol based on the realistic scenarios.

Power management system for Multi-Input Multi-Output energy harvesters using fuzzy logic

With the increase in energy consumption, the concept of harvesting energy in the surroundings awaken a renewed interest. Scarcity of resources has been a great matter to all and researchers have been innovating new methods in harvesting energy. A power management system (PMS) is needed to manage and maximize the output energy coming from the piezoelectric and solar photovoltaic harvesters. However, there is no existing PMS for Multi-Input Multi-Output (MIMO) specified for the said harvesters. Hence, this paper focuses on the development of a fuzzy logic controller implemented in the PMS with the use of Fuzzy Interface System of MATLAB in order to achieve a better overall performance and utilization of the distribution of the generated energy from the harvester. In addition, the simulation and behavior of the decision making for the PMS was obtained.

An automated road traffic congestion estimating program

Video processing techniques have been used in determining road traffic conditions and it proved itself quite useful but still cannot adapt to changes in the environment lighting. Human intervention is required to input the new background which would require effort. The project focuses on the creation of a program that uses background elimination in extracting the foreground objects. However, to solve the problems regarding change in lighting, the background estimating algorithm must be adaptive to this change. It uses the Kalman tracking equations to derive the mean update and standard deviation using tuned values of measurement noise covariance and process noise covariance. The background to be subtracted will then update itself depending on the changes in lighting during the video stream and any slight movement of the camera itself. Blob analysis is then used to gather data. Total blob area and centroid movement are the parameters to be considered in the programs decision making and fuzzy logic is used to decide given these parameters. The output is displayed as an embedded text in the original video. The whole program is created and simulated in the MatLab environment using its “vision” package.

Depth map characterization of RGB-D sensor for obstacle detection system

This paper presents a characterization of the depth map from an RGB-D sensor, Kinect 360, to be used as an input to an obstacle detection system. Since the accuracy, reliability and timeliness of the data are crucial in the system, there is a need to characterize it. Sensor repeatability tests are done to characterize the depth map. The mean and standard deviation of measured depths and mean error were computed to describe its detection accuracy and precision. Evident noises during tests were defined.

Autonomous trajectory tracking of a quadrotor UAV using PID controller

Quadrotor helicopters are becoming popular rotorcrafts for unmanned aerial vehicles (UAV) platforms because of its simplicity, high maneuverability and the ability to withstand harsh environments without the risk of human intervention. This now imposes a demand in areas of control and navigation. For the quadrotor to follow a desired path, a controller must be able to track its trajectory and ensure that the error is minimal with the presence of external disturbances. The study will utilize the use of a PID as the controller of the Quadrotor UAV. PID controller is popular because it has good control performance and is easy to implement but the changing of its coefficients are performed manually.

Modified shape independent method in detecting pedestrians using FIR cameras at night

Major percentage of car accidents occur during nighttime due to the lack of sunlight, making it difficult to see external factors like control devices, traffic flow and road markings between the vehicle and its surroundings. With these parameters, car safety systems; active and passive, are developed to prevent car accidents. Some active systems developed for night vision are for imminent rear end collision, overtaking vehicles, blind spots and pedestrians but pedestrians are more vulnerable in car accidents. This led the researchers to develop the modified shape independent method to accurately detect pedestrians at night time. For night vision, IR cameras provides clear pixels but with regards to pedestrian, FIR camera provides the thermographic patterns that will detect pedestrians from non-pedestrian regions. The studys main concern in this study is to accurately detect pedestrians on the roadside. High-temperature objects with thermographic patterns assumed to be pedestrians and are detected by processing the images from infrared cameras attached on the vehicle. In the course of this study, the researchers were able to detect pedestrians consistently with an 86.27% accuracy.