Search

Numerous sensor fusion techniques have been reported in the literature for a number of robotics applications. These techniques involved the use of different sensors in different configurations. However, in the case of food driving, the possibility of the implementation has been overlooked. In restaurants and food delivery spots, enhancing the food transfer to the correct table is neatly required, without running into other robots or diners or toppling over. In this project, a particular algorithm module has been proposed and implemented to enhance the robot driving methodology and maximize robot functionality, accuracy, and the food transfer experience. The emphasis has been on enhancing movement accuracy to reach the targeted table from the start to the end. Four major elements have been designed to complete this project, including mechanical, electrical, electronics, and programming. Since the floor condition greatly affecting the wheels and turning angle selection, the movement accuracy was improved during the project. The robot was successfully able to receive the command from the restaurant and go to deliver the food to the customers' tables, considering any obstacles on the way to avoid. The robot has equipped with two trays to mount the food with well-configured voices to welcome and greet the customer. The performance has been evaluated and undertaken using a routine robot movement tests. As part of this study, the designed service wheeled robot required to be with a high-performance real-time processor. As long as the processor was adequate, the experimental results showed a highly effective search robot methodology. Having concluded from the study that a minimum number of sensors are needed if they are placed appropriately and used effectively on a robot's body, as navigation could be performed by using a small set of sensors. The Arduino Due has been used to provide a real-time operating system. It has provided a very successful data processing and transfer throughout any regular operation. Furthermore, an easy-to-use application has been developed to improve the user experience, so that the operator can interact directly with the robot via a special setting screen. It is possible, using this feature, to modify advanced settings such as voice commands or IP address without having to return back to the code.

This thesis focuses on developing software for mobile robots which enables these platforms to perform household tasks. A set of tasks was proposed by the RoboCup Federation for the 2019 RoboCup@Home competition. The primary goal of this competition is to develop a unified robotic system with the capability to assist humans in their daily lives. Efforts toward this competition were made through collaboration with the Austin Villa team at The University of Texas at Austin. Toyota's Human Support Robot served as the robotic platform for the competition. This thesis primarily focuses on a task in which the robot autonomously collects trash bags and transports them to a designated location. Cooking is another household task addressed in this thesis. In particular, this work examines methods of enabling a robotic system to understand the cooking process and use this understanding to make informed decisions. The case study that was analyzed involves using a Convolutional Neural Network to process image data and estimate when a pancake has been sufficiently cooked. The work in this thesis contributes toward development of tools for mobile service robots in domestic environments. These tools are also implemented and shown to be effective in enabling robots to improve quality of life by assisting in household chores.

This thesis focuses on developing software for mobile robots which enables these platforms to perform household tasks. A set of tasks was proposed by the RoboCup Federation for the 2019 RoboCup@Home competition. The primary goal of this competition is to develop a unified robotic system with the capability to assist humans in their daily lives. Efforts toward this competition were made through collaboration with the Austin Villa team at The University of Texas at Austin. Toyota's Human Support Robot served as the robotic platform for the competition. This thesis primarily focuses on a task in which the robot autonomously collects trash bags and transports them to a designated location. Cooking is another household task addressed in this thesis. In particular, this work examines methods of enabling a robotic system to understand the cooking process and use this understanding to make informed decisions. The case study that was analyzed involves using a Convolutional Neural Network to process image data and estimate when a pancake has been sufficiently cooked. The work in this thesis contributes toward development of tools for mobile service robots in domestic environments. These tools are also implemented and shown to be effective in enabling robots to improve quality of life by assisting in household chores.

Generally, patients are needed to lift and move by doctors, nurses or medical assistances in the hospital. Simple pick and place patient is the usual way performing in hospitals and other medical services, particularly during emergent situations, within the operating room or changing to another hospital room or transporting to the other hospital. Transporting procedure are mainly essential for paralyzed or obese patients. In this present study, the robot called Clinicon, was presented with the feasibility and conceptual design to assist the medical teams to transport and also to position the patients particularly in the operating room with safety concern. The first main conceptual system of Clinicon consists of the line follow tracking system and the designed manipulator for transporting and positioning the patient to perform the task only in the operating room. However, this is still the conceptual design, the practical version robot; Clinicon, is quite challenge to be built in the future.