Browsing by Author "Tsoeu, Mohohlo Samuel"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Open Access
    Energy efficient path planning: the effectiveness of Q-learning algorithm in saving energy
    (2014) Ogunniyi, Samuel; Tsoeu, Mohohlo Samuel
    In this thesis the author investigated the use of a Q-learning based path planning algorithm to investigate how effective it is in saving energy. It is important to pursue any means to save energy in this day and age, due to the excessive exploitation of natural resources and in order to prevent drops in production in industrial environments where less downtime is necessary or other applications where a mobile robot running out of energy can be costly or even disastrous, such as search and rescue operations or dangerous environment navigation. The study was undertaken by implementing a Q-learning based path planning algorithm in several unstructured and unknown environments. A cell decomposition method was used to generate the search space representation of the environments, within which the algorithm operated. The results show that the Q-learning path planner paths on average consumed 3.04% less energy than the A* path planning algorithm, in a square 20% obstacle density environment. The Q-learning path planner consumed on average 5.79% more energy than the least energy paths for the same environment. In the case of rectangular environments, the Q-learning path planning algorithm uses 1.68% less energy, than the A* path algorithm and 3.26 % more energy than the least energy paths. The implication of this study is to highlight the need for the use of learning algorithm in attempting to solve problems whose existing solutions are not learning based, in order to obtain better solutions.
  • Thumbnail Image
    Item
    Open Access
    Imitating human motion using humanoid upper body models
    (2012) Dube, Chioniso; Tsoeu, Mohohlo Samuel; Tapson, Jonathan
    This thesis investigates human motion imitation of five different humanoid upper bodies (comprised of the torso and upper limbs) using human dance motion as a case study. The humanoid models are based on five existing humanoids, namely, ARMAR, HRP-2, SURALP, WABIAN-2, and WE-4RII. These humanoids are chosen for their different structures and range of joint motion.
  • Thumbnail Image
    Item
    Open Access
    South African sign language dataset development and translation : a glove-based approach
    (2014) Mcinnes, Ben; Tsoeu, Mohohlo Samuel
    There has been a definite breakdown of communication between the hearing and the Deaf communities. This communication gap drastically effects many facets of a Deaf person’s life, including education, job opportunities and quality of life. Researchers have turned to technology in order to remedy this issue using Automatic Sign Language. While there has been successful research around the world, this is not possible in South Africa as there is no South African Sign Language (SASL) database available. This research aims to develop a SASL static gesture database using a data glove as the first step towards developing a comprehensive database that encapsulates the entire language. Unfortunately commercial data gloves are expensive and so as part of this research, a low-cost data glove will be developed for the application of Automatic Sign Language Translation. The database and data glove will be used together with Neural Networks to perform gesture classification. This will be done in order to evaluate the gesture data collected for the database. This research project has been broken down into three main sections; data glove development, database creation and gesture classification. The data glove was developed by critically reviewing the relevant literature, testing the sensors and then evaluating the overall glove for repeatability and reliability. The final data glove prototype was constructed and five participants were used to collect 31 different static gestures in three different scenarios, which range from isolated gesture collection to continuous data collection. This data was cleaned and used to train a neural network for the purpose of classification. Several training algorithms were chosen and compared to see which attained the highest classification accuracy. The data glove performed well and achieved results superior to some research and on par with other researchers’ results. The data glove achieved a repeatable angle range of 3.27 degrees resolution with a standard deviation of 1.418 degrees. This result is far below the specified 15 degrees resolution required for the research. The device remained low-cost and was more than $100 cheaper than other custom research data gloves and hundreds of dollars cheaper than commercial data gloves. A database was created using five participants and 1550 type 1 gestures, 465 type 2 gestures and 93 type 3 gestures were collected. The Resilient Back-Propagation and Levenberg-Marquardt training algorithms were considered as the training algorithms for the neural network. The Levenberg-Marquardt algorithm had a superior classification accuracy achieving 99.61%, 77.42% and 81.72% accuracy on the type 1, type 2 and type 3 data respectively.
  • Thumbnail Image
    Item
    Open Access
    Towards improving the Statscan X-ray image quality through sliding mode control of the C-arm
    (2012) Esmail, Mohammed; Tsoeu, Mohohlo Samuel; John, Lester
    This dissertation investigates methods for improving the image quality of a digital radiography system. The Lodox Statscan™ X-ray system provides a full-body scanned image for initial diagnosis. The system is driven by a permanent magnet linear motor (PMLM) controlled by a cascaded proportional-proportional integral controller (P-PI). Transient errors in the trapezoidal motion profile of the scanning C-arm may cause mismatches between the detector and the collimated beams from the X-ray source. This results in a partial degradation of image quality. The Statscan™ X-ray system was investigated and the following constraints were identified: The scanning time is limited to 13 seconds and the maximum scan length is limited to 1.8 m. Since it was not possible to obtain the Lodox Statscan™ dynamics model, because of the similarity, a characteristic model was then developed using a DC motor in order to investigate the control dynamics. It is not advisable for a designer to manipulate the controllers on commercial machines except for changing the parameters for tuning. Therefore, a P-PI controller and a proportional-integral sliding mode controller (P-ISMC) as well as a Boundary Layer variant (P-ISMC+BD) were designed for fair comparison purposes. Root locus, Bode diagrams and integral sliding mode control methods, respectively, were used to design the P-PI and P-ISMC controller groups. Each controller consists of an inner loop and an outer position loop. Proportional integral (PI) and integral sliding mode controllers (ISMC) were used for the inner loop. The two inner loop controllers were tuned, and then tested, before cascading them with the outer position loop. The simulation and experiments were conducted to compare each controller’s performance on step set-point tracking, trapezoidal motion profile tracking, the time transient’s specifications and robustness against disturbances. In order to test image quality, 27 distance profiles were generated from P-PI, P-ISMC and P-ISMC+BD. In addition, four images captured by the Statscan™ were also selected. A time delay integrator (TDI) simulator was used on the distance profiles and the four images to generate 108 distorted image profiles.