Browsing by Author "Stopforth, Riaan."

Now showing 1 - 14 of 14

Autonomous sea craft for search and rescue operations : marine vehicle modelling and analysis.
(2011) Onunka, Chiemela.; Bright, Glen.; Stopforth, Riaan.
Marine search and rescue activities have been plagued with the problem of risking the lives of rescuers in rescue operations. With increasing developments in sensor technologies, it became a necessity in the marine search and rescue community to develop an autonomous marine craft to assist in rescue operations. Autonomy of marine craft requires a robust localization technique and process. To apply robust localization to marine craft, GPS technology was used to determine the position of the marine craft at any given point in time. Given that the operational environment of the marine was at open air, river, sea etc. GPS signal was always available to the marine craft as there are no obstructions to GPS signal. Adequate cognizance of the current position and states of an unmanned marine craft was a critical requirement for navigation of an unmanned surface vehicle (USV). The unmanned surface vehicle uses GPS in conjunction with state estimated solution provided by inertial sensors. In the absence of the GPS signal, navigation is resumed with a digital compass and inertial sensors to such a time when the GPS signal becomes accessible. GPS based navigation can be used for an unmanned marine craft with the mathematical modelling of the craft meeting the functional requirements of an unmanned marine craft. A low cost GPS unit was used in conjunction with a low cost inertial measurement unit (IMU) with sonar for obstacle detection. The use of sonar in navigation algorithm of marine craft was aimed at surveillance of the operational environment of the marine craft to detect obstacles on its path of motion. Inertial sensors were used to determine the attitude of the marine craft in motion.
Bio-mechatronic implementation of a portable upper limb rehabilitative exoskeleton.
(2011) Naidu, Dasheek.; Stopforth, Riaan.; Bright, Glen.; Davrajh, Shaniel.
The rationale behind this research originates from the lack of public health care in South Africa. There is an escalation in the number of stroke victims which is a consequence of the increase in hypertension in this urbanising society. This increase results in a growing need for physiotherapists and occupational therapists in this country which is further hindered by the division between urban and rural areas. The exoskeleton device has been formulated to encapsulate methodologies that enable the anthropomorphic integration between a biological and mechatronic limb. The physiotherapeutic mechanism was designed to be portable and adjustable, without limiting the spherical motion and workspace of the human arm. The exoskeleton was portable in the sense that it could be transported geographically and is a complete device allowing for motion in the shoulder, elbow, wrist and hand joints. The avoidance of singularities in the workspace required the implementation of non-orthogonal joints which produces extensive forward kinematics. Traditional geometric or analytical derivations of the inverse kinematics are complicated by the nonorthogonal layout. This hindrance was resolved iteratively via the Damped Least Squares method. The electronic and computer system allowed for professional personnel, such as an occupational therapist or a physiotherapist, to either change an individual joint or a combination of joints angles. A ramp PI controller was established to provide a smooth response in order to simulate the passive therapy motion.
Contractible arms elevating search and rescue (Caesar) robot : improvements and modifications for urban search and rescue (Usar) robots.
(2010) Stopforth, Riaan.; Bright, Glen.; Harley, Ronald G.
Rescuers have lost their lives in events requiring them to go into dangerous areas that have unstable structures and gases. Robots are necessary for search and rescue purposes, to access concealed places and environments to which fire fighters and rescue personnel cannot gain entry. Robots that were previously used encountered problems with communication, chassis design, traction and sensory systems. Improvements are required for the successful localization of victims. Research on improvements in these areas were carried out for the use in the CAESAR (Contractible Arms Elevating Search And Rescue) robot. Contributions were made in the area of Urban Search And Rescue (USAR) robots focusing on antenna design, communication protocols, chassis design, traction system and artificial intelligence on decisions relating to gas danger levels for humans and the robot. The capabilities of CAESAR is audio, video and data communication irrespective of the orientation of the robot and the antennas. Penetration of radio frequencies through building material is possible. Reliable data communication is achieved with the designed Robotics Communication Protocol (RCP). The chassis is designed to have traction on unstable terrain and autonomously transform flipper arms for the best orientation. Materials for the body were selected and constructed to be able to withstand the unstable environments and high temperatures which they will encounter. The control station display gives the rescuers immediate indication of the gas concentrations detected by the on-board gas sensors. Developed analytical models determine the danger of the gas concentrations for victims, rescuers and the robots.
The cooperation of heterogeneous mobile robot configurations in advanced manufacturing environments.
(2014) Naidoo, Nicol.; Bright, Glen.; Stopforth, Riaan.
Cooperation of Multiple Mobile Robot Systems (MMRS) have drawn increasing attention in recent years since these systems have the ability to perform complex tasks more efficiently compared to Single Mobile Robot Systems (SMRS). An implementation of a cooperative MMRS in a manufacturing environment can, for example, solve the issue of bottlenecks in a production line, whereas the limitations of a SMRS can lead to a lot of problems in terms of time wastage, loss of revenue, poor quality products and dissatisfied customers. The study of cooperation in heterogeneous robot teams has evolved due to the engineering and economic benefits attribute as well as the existence of diversities in homogeneous robot teams. The challenge of cooperation in these systems is a result of the task taxonomies and fundamental abilities of each robot in the team; there is therefore a need for an Artificial Intelligence (AI) system that processes these heterogeneities to facilitate robot cooperation. This dissertation focuses on the research, design and development of an artificial intelligence for a team of heterogeneous mobile robots. The application of the system was directed towards advanced manufacturing systems, however, it can be adapted to search and rescue tasks. An essential component of the AI design is the machine learning algorithm which was used to predict suitable goal destinations for each mobile robot, given a set of input parameters. Mobile robot autonomy was achieved through the development of an obstacle avoidance and navigation system. The AI was also interfaced to a Supervisory Control and Data Acquisition System (SCADA) which facilitates end-user interaction - a vital ingredient to manufacturing automation systems.
A distributed framework for the control and cooperation of heterogeneous mobile robots in smart factories.
(2017) Naidoo, Nicol.; Bright, Glen.; Stopforth, Riaan.
The present consumer market is driven by the mass customisation of products. Manufacturers are now challenged with the problem of not being able to capture market share and gain higher profits by producing large volumes of the same product to a mass market. Some businesses have implemented mass customisation manufacturing (MCM) techniques as a solution to this problem, where customised products are produced rapidly while keeping the costs at a mass production level. In addition to this, the arrival of the fourth industrial revolution (Industry 4.0) enables the possibility of establishing the decentralised intelligence of embedded devices to detect and respond to real-time variations in the MCM factory. One of the key pillars in the Industry 4.0, smart factory concept is Advanced Robotics. This includes cooperation and control within multiple heterogeneous robot networks, which increases flexibility in the smart factory and enables the ability to rapidly reconfigure systems to adapt to variations in consumer product demand. Another benefit in these systems is the reduction of production bottleneck conditions where robot services must be coordinated efficiently so that high levels of productivity are maintained. This study focuses on the research, design and development of a distributed framework that would aid researchers in implementing algorithms for controlling the task goals of heterogeneous mobile robots, to achieve robot cooperation and reduce bottlenecks in a production environment. The framework can be used as a toolkit by the end-user for developing advanced algorithms that can be simulated before being deployed in an actual system, thereby fast prototyping the system integration process. Keywords: Cooperation, heterogeneity, multiple mobile robots, Industry 4.0, smart factory, manufacturing, middleware, ROS, OPC, framework.
The electromyography, electronics and sensory system for a mechatronics integrated touch hand 3.
(2016) Mangezi, Andrew.; Stopforth, Riaan.
This research presents the EMG, electronics and sensory system for a mechatronics integrated Touch Hand 3. This unique myoelectric hand was driven by EMG signals captured at the surface of the skin in order to achieve a more robust grasp. The research consisted of different configurations and types of electrodes to be used for an EMG device, with the research analysis of the different candidates to control the Touch Hand 3. In addition, the EMG experimental results to compare contact and non-contact electrodes were carried out to find a correlation between the EMG electrodes and an antenna. These results determined the number of layers that the EMG sensor will need to obtain the best reading in a patch-yagi antenna. Stick-on electrodes were used to monitor two muscle groups in the arm at the same time. Contact and non-contact electrode tests were conducted, which used a combination of the embroidery electrodes and the stick-on electrodes. The flexion-extension muscles were tested in the experiments, by letting each volunteer lift a 2.5 kg weight. The electronics and sensor system had to be researched, designed, developed and optimized to allow for a successful integration of the Touch Hand 3. The artificial arm is fitted with palpable sensors to read the object temperature, force, and vibration. A number of constraints were considered in designing the system including the modularity of the system, cost, weight, and its grip strength in comparison with the Touch Hand 2. The modular electrical system was designed to accommodate full control and integration with the mechanical system to form a myoelectric mechatronics prosthetic system to be used by the amputees more effectively in a quicker response.
Integration of a wearable IoT-based smart healthcare system with predictive modelling.
(2021) Govender, Pragesh Ashley.; Stopforth, Riaan.; Sivarasu, S.; Markus, E.; Hands, Clive.
Abstract: The usage of the Internet of things (IoT) equipped with intelligent machine learning (ML) or fuzzy logic (FL) systems in the medical sector is becoming a widespread normality. This following the implications of the 4th and 5th industrial revolutions (5IRs) aiming to integrate technology with the way we live and work. Many research areas have focused on incorporating individual elements of an intelligent IoT based system. However, none have holistically looked at encompassing a multi-faceted sensory device with an IoT framework backed by both ML and FL capabilities for unique monitoring and diagnostics. This implies that there is an opportunity to create such a product targeted for the medical sector. The developed system of systems (SoS) discussed therefore aims at eliminating the barrier to patient care outside of a hospital setting through the use of real time patient diagnostics. The study was approached by first establishing a streamlined IoT infrastructure. A multi-faceted Arduino based sensory device was then developed to collect user parameters. The electronics were housed in a common of the shelf (COTS) casing satisfying the criteria of wearability. Bluetooth connectivity then allowed for the transmission of sensory data from the WBAN to the IoT smartphone gateway. Sensory parameters being measured were electrocardiography (ECG), electromyography (EMG), body temperature (BT), infrared (IR) output, pulse rate (PR) as well as environmental humidity readings. Blood sugar (BS) levels were obtained non-invasively by calibrating the IR output voltage with that of a calibrated glucometer to obtain a straight line equation representing the relationship between the sensor ADC output and glucose in the blood. A Java based mobile application (MA) was then developed, which allowed for the processing of the sensory data before storage in a local SQLite database. A two interface MA for use by registered doctors and patients was necessary to allow for data sharing and security. Registration and login for the MA was done through a NoSQL Firebase database. A JDBC was established to enable the transmission of data to a MS Azure Structured Query Language (SQL) database. This served as the cloud interface within the IoT network layer. The MA is able to integrate with a phone’s Global Positioning System (GPS) to allow for simultaneous tracking of patients. A return application programming interface (API) connection between MS Azure and the developed application layers was then created. Here the mobile doctor interface as well as a developed node.js based web application (WA) served as the mediums through which health practitioners could access patient data. ML models were developed using the MS Azure ML Classic Studio suite which allowed for a real time analysis of received data through deployment and subsequent consumption of data using POST Requests via the MA and a Java software development kit (SDK). An accuracy of 92% was achieved for the stroke prediction model based on the boosted decision tree algorithm. Various ML models were analyzed to ensure that a high precision was obtained while preventing overfitting. Additional FL models were also developed, which took into consideration unique sets of vitals combinations to create a rule base depicting the patient health status and health risk. v This data was compared to the intuition of a doctor and received an 87% accuracy for model 1 which took into consideration a patient’s PR, BS, BT and age to predict the health status of a patient. The model was then compared to the Modified Early Warning Score (MEWS) rating, a popular measure of health risk utilized in the medical field. The results of comparison also yielded an accuracy of 87%. A second FL model was then developed looking at the effect of environmental conditions on the risk rating of patients. Here input variables of BT, age and humidity readings were used to determine their effect the on the risk rating of a patient. This model scored an 80% accuracy when compared to the expertise of a physician. Both models were programmed onto the MA to predict the patient’s health status. Both models were also re-developed on MATLAB software to simulate the effect of various input variables on the response variable. Overall the designed system was able to possess around 15 of the typical features found in smart wearable systems which far exceeded the features of those devices it was compared to. The designed system satisfied the requirement of a feature rich experience while also satisfying the criteria of cost effectiveness.
Mechanical design of a biologically inspired prosthetic hand, the touch hand 3.
(2017) Fourie, Riaan Gerard.; Stopforth, Riaan.
The Touch hand 3 was developed to improve on the mechanical and mechatronic design of the Touch hand 2. A basic prototype hand was rapidly developed using 3D CAD software and 3D printing and tested on an amputee. The improvements in the final design included an improved finger actuation system utilizing mechanical linkages, an improved Electromyography (EMG) operated control system, four micro-linear servo-motors, modular fingers, hinges and chassis. The final design was designed such that the hand can be easily interchanged between a fully mechatronic system and full mechanically operated system using the same generic parts including the chassis, finger and wrist components. The hands were both tested with the Yale Open Hand test, a test used to assess robotic grippers. The Southampton Hand Assessment Procedure (SHAP), a test usually used to assess the effectiveness of upper limb prostheses, was also carried out on both versions of the hand. The hands were also tested with a hand dynamometer to assess their grip strength. The hand were compared to current hands on the market and their strength and weaknesses analysed.
Mechatronic design and optimisation of a low-cost prosthetic hand.
Jones, Gregory Kyle.; Stopforth, Riaan.
The Touch Hand II was developed to improve on the first version, addressing the lack of low cost myoelectric controlled hand prostheses. The improvements included a lower materials cost of $ 635.14, an aesthetically appealing human{like form factor, a reduced total mass of 486 g (including the wrist and electronics), a 211 % increase in grip strength, and a 3.83 times higher allowable palm load with a 1.7 factor of safety. Costs were reduced predominantly due to 3D printing and using sensorless technology, based on speed and torque estimation through brushed dc motor back-emf and current measurements. The compact design was accomplished by using a unique finger actuation and trajectory concept, and integrating a custom PCB. An intuitive command selection protocol was developed with the aid of a GUI. A finite state machine was used to successfully switch between speed and grip force control depending on whether an object was in contact with the fingers during a close/open command. The design has accommodated the future addition of myoelectric control, sensors, and sensory feedback.
Mechatronics integration for a vehicle simulator.
(2016) Kader, Taahir.; Stopforth, Riaan.; Bright, Glen.
This dissertation presents the research and integration of a mechatronics system to be used in a vehicle simulator. The vehicle simulator is comprised of a 3-DOF platform which is used to provide motion cues to the driver. Kinematic analysis is performed on the 3-DOF system and this analysis assists in implementing platform motion control. To recreate the motion sensations experienced in an actual vehicle while respecting the platform workspace limits the classical washout algorithm is implemented in the vehicle simulator. A novel simulation system was contributed in Matlab/Simulink to aid in vehicle simulator design. This simulation setup incorporates all the motion cueing aspects; these aspects include input vehicle data scaling, the classical washout algorithm and inverse kinematic analysis. The developed simulation system was used to adjust the motion cueing parameters to ensure motion that respects the actuator motion constraints. These constraints ensure the vehicle simulator is operated safely. A second contribution used the developed simulation system in Matlab/Simulink and the human vestibular system models. A performance evaluation was performed on the 3-DOF system against the traditional 6-DOF system. The results highlight the benefits of the 3-DOF system in replication of certain motion cues. Software was developed to receive input game data and output actuator stroke lengths to the motion control system. Limitations in the motion control system were found when testing was done on the vehicle simulator. These limitations led to a modified partial 2-DOF vehicle simulator. The motion control hardware is able to replicate actuator motion well. The final vehicle simulator system is a partial 2-DOF system that provides visual and motion cues that create a realistic driving experience. The developed system is suitable for applications with cost constraints and reasonable performance requirements.
A modular prosthetic arm with haptic interfacing for transradial/transhumeral amputees.
(2014) Van der Riet, Drew.; Stopforth, Riaan.; Bright, Glen.; Diegel, Olaf.
Contemporary upper extremity prosthetics bring a lot of benefit to the amputee community. However, there are still a number of challenges facing the field of upper extremity prosthetics. These challenges include high cost and low functionality. This dissertation looks into a low-cost solution to provide a modular upper extremity prosthetic that will be suitable for both transradial and transhumeral amputees. A novel method of myoelectric control is investigated with the introduction of a haptic user interface which will enhance the functionality of the prosthesis. This approach uses haptic feedback to display information (through the use of haptic displays) about the status of the control of the prosthetic arm. The hand of the prosthetic arm is equipped with tactile sensors. These sensors read grip force, object slip, object temperature and object texture. In a novel approach to haptic feedback, this sensory information is displayed to the user simultaneously through a multi-sensory haptic feedback system. The haptic display uses vibrotactile displays to communicate the information to the user through vibrations. This approach gives the user a more holistic sensory representation. The UKZN Touch Hand was developed at a cost of US$ 1’000 for materials and parts. It is capable of gripping with 19.5 N using a power/cylindrical grip and 3.7 N using a lateral/key grip. It can hold up to 8 kg passively using a hook grip. The hand weighs 540 g including all electronics. It is equipped with pressure, temperature and vibration sensors to sense grip force, object temperature, slippage and texture. A novel simultaneous multi-sensory haptic feedback system was designed, tested on nine test subjects and shown to be a suitable form of feedback using a single vibrotactile display per sensory channel. A novel electromyography control method was developed to allow the amputee to select from a limitless list of pre-set grip types and hand gestures using only two muscles. The Touch Hand was successfully tested on a transradial amputee who used it to perform tasks such as picking up various objects, pouring a bottle of water and drinking from a cup. Future work in this research should investigate alternative haptic feedback communication protocols to optimise the communication of information. Future work should also be done in developing fitting and training software to improve the amputees fitting and learning experience of the control of the prosthetic hand.
Software integration for human detection in mining UAV systems.
(2013) Motepe, Sibonelo.; Stopforth, Riaan.
Mining is one of the main economic sectors in South Africa. Mining activity contains hazards such collapsing of structures, presence of dangerous gases, accidental explosions and fires. Even though most of these hazards are identified and minimized sometimes accidents occur. These accidents lead to human injuries, direct fatalities and fatalities resulting from delays in victims getting medical attention as a result of delays in search and rescue missions. The rescue missions in underground mines present challenges where rescuers are not sure which locations are victims in, what the area conditions like in the rescue path. A quad rotor unmanned aerial vehicle (UAV) for search and rescue missions is presented. The UAV is controlled from a remote location over Wi-Fi. The communication allows data relay to the ground control station. The communication system is tested on the university’s Wi-Fi network. The UAV also contains a vision system that contains a human detection algorithm to give an indication of human presence to rescuers. The human detection system is based on Haar- Cascade classifiers. The model developed was found to have a false alarm rate of 5×10-3% after training. The model was further tested on streaming data and the overall average positive human detection was found to be 97 %. In the same tests overall false average detection was found to be 2.5 %. The video feed is streamed from the UAV to the ground station (GS) and the flight control instructions are sent to the UAV from the GS via Wi-Fi.
System integration of a remotely accessible satellite tracker.
(2022) Kisoon, Rushil.; Stopforth, Riaan.
The recent rise in space missions and satellite launches has piqued the interest of many. As a result, the growing number of objects in orbit has led to an increase in space monitoring. While large-scale tracking systems exist, many enthusiasts utilise rudimentary methods for satellite monitoring. Some have created do-it-yourself rotators or radio reception stations. Subsequently, a remotely accessible system was required to track satellites and receive transmissions. A small-scale system was designed to fulfil the requirements. Aluminium extrusions were used to create the frame, while microprocessors, sensors and other components were integrated to complete the rotator assembly. A circuit layout was drawn up to coordinate the flow of power and data between components. Low-powered electronics allow the system to run off-grid via a 12 V battery. Many features of the Raspberry Pi lent well to the required application, such as wireless network connectivity and a remote access service. Gpredict, an advanced satellite tracking software, was used to calculate the coordinates for rotation. The RTL-SDR, a software-controlled tuner, provided control to receive radio frequencies. Features such as a slow scan image decoder and frequency identification toolkit were also integrated. The user interface program called TrackGUI was coded, which allows easy access to tracking features. A login system was created with ‘admin’ and ‘user’ access levels. Initially, the presence of GlobalProtect on the UKZN network posed an issue, but methods were implemented to solve this problem. Various aspects of the system were tested and iterated until they met the required parameters. Test results showed that the system could operate within 5 degrees of the intended target. Radio transmissions and slow-scan images could be received and recorded. Therefore, the aim of integrating hardware and software components to create a remotely accessible satellite tracking system was achieved.
Techniques and countermeasures of TCP/IP OS fingerprinting on Linux Systems
(2007) Stopforth, Riaan.; Vorster, Luke Anthony.; Erwin, David.
Port scanning is the first activity an attacker pursues when attempting to compromise a target system on a network. The aim is to gather information that will result in identifying one or more vulnerabilities in that system. For example, network ports that are open can reveal which applications and services are running on the system. How a port responds when probed with data can reveal which protocol the port utilises and can also reveal which implementation of that protocol is being employed. One of the most valuable pieces of information to be gained via scanning and probing techniques is the operating system that is installed on the target. This technique is called operating system fingerprinting. The purpose of this research is to alert computer users of the dangers of port scanning, probing, and operating system fingerprinting by exposing these techniques and advising the users on which preventative countermeasures to take against them. Analysis is performed on the Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Internet Protocol (IPv4 and IPv6), and the Internet Control Message Protocol (ICMPv4 and ICMPv6). All the software used in this project is free and open source. The operating system used for testing is Linux (2.4 and 2.6 kernels). Scanning, probing, and detection techniques are investigated in the context of the Network Mapper and Xprobe2 tools.