Browsing by Author "Verrinder, Robyn A"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- ItemOpen AccessBiologically inspired goal directed navigation for mobile robots(2016) Amayo, Paul Omondi; Verrinder, Robyn AThis project involved an investigation into low-cost navigation of mobile robots with the aim of creating and adaptive navigation system inspired by behaviour seen in animals. The navigation module developed here would need to be able to successfully localise a robot and navigate it to a defined target. A critical literature review was carried out of current localisation and path-planning architectures and a bio-inspired approach using an Echo State Network and Liquid State Machine architecture was chosen as the base for the navigation modules. The navigation module implemented in this work is trained to navigate and localise itself in different environments drawing its inspiration from the behaviour of small rodents. These architectures were adapted for use by a robot with a view on the physical implementation of these architectures on an embedded low-cost robot using a Raspberry Pi computer. This robot was then built using low-cost, noisy proximity sensors which formed the inputs to the navigation modules. Before the deployment on the embedded robot the system was tested and validated in a full physics simulator. While the training of the Echo State Networks and Liquid State Machine has been carried out in the literature by the offline method of linear regression, in this work we introduce a novel way of training these networks that is online using concepts from adaptive filters. This online method increases the adaptability of this system while significantly decreasing its memory requirements making it very attractive for low-cost embedded robots. The end result from the project was a functioning navigation module using an Echo State Network that was able to navigate the robot to a target position as well as learn new paths, either using offline or online methods. The results showed that the Echo State Network approach was valid both in simulation and practically as a base for creating navigation modules for low-cost robots and could also lead to more efficient and adaptable robots being developed if the training was carried out in an online manner. The increased computational complexity of implementing the liquid State machine on analytical machines however made it unsuitable for deployment on robots using embedded micro-controllers.
- ItemOpen AccessCollaborative control of wave glider platforms - Local Communication and Sea State Estimation(2019) Fangbemi, Kossivi Agbessi; Boje, Edward; Verrinder, Robyn AClimate change is the focus of many oceanography and marine engineering researchers, with possible links between climate change and the carbon cycle in the Southern Ocean being considered. This type of investigation requires modern and cost-effective tools to conduct surveys and collect data from the ocean. The self-propelled unmanned surface vessel, the Liquid Robotics Wave Glider, was designed primarily as a marine research tool and offers several advantages over existing research vessels and other tools employed for data acquisition in the ocean. The main advantages are its robustness at sea, i.e. its ability to withstand extreme weather conditions, its propulsion energy source, which is the wave energy, and its customisable electronics payload. The inter-platform communication strategy of the Wave Glider inspired a few engineering questions, one of which is the focal point of this research: whether Low Power Wide Area Network (LPWAN) technology can be used to set up a local communication system enabling the collaboration of two or more Wave Gliders and reduce the cost, in terms of power and communication channels, involved in the communication with the Wave Glider platforms during missions. This research considers various LPWAN technologies available on the market and proposes LoRaWAN technology for the local communication system. LoRaWAN was selected as it presented a robust radio modulation and had growing support in the industry. In this research, a LoRa-based network of two nodes was developed, implemented and tested over the surface of the ocean. It was found that the system performs well over a distance of 1 km with both antennas having one end at the mean surface level of the sea. With the intention to increase the range of the platform and achieve a reliable and robust system, the research continued with the study of the influence of the surface waves on the proposed local communication system by exploring, firstly, the impact of seawater and, secondly, the wave height on signal transmission. The first study investigated the influence that the electromagnetic properties of seawater may have on the transmission of signals from one node to the second through simulations using the computational electromagnetic package FEKO. It revealed that, at the frequency of operation, which was 868 MHz, seawater reacted as a lossy conductor and reflected the signal upward, with negligible power penetrating the surface of the ocean. The subsequent study reviewed the statistical properties of the ocean surface waves in a sea of deep waters and proposed a relationship between the wind speed (or surface wave elevation), the antenna height, the distance separation between the two nodes and the probability of the presence of a line of sight (LoS) between the two nodes. This relationship quantifies the expected result that the probability of the LoS diminishes as the wind speed or the distance between the two nodes increases, whereas it improves with an increase in the antenna height. The last part of the research focused on initial works on sea state estimation using the lossless wave equation and Kalman Filter to provide 3D sea surface elevations that would be used to change to the probability of the LoS calculated previously in the research. Indeed, using the local communication to share the point-wise sea state data can be exploited to estimate the sea state over a rectangular region delimited to include these points. Sea state estimation is expected to enhance the joint navigation and coordination of the platforms and consequently, boost the probability of the LoS through the transmission at the crest of the waves. During the development of the Kalman Filter model, it was discovered that the sample time and the sample space significantly affect the performance and the stability of the discretised models. However, a carefully selected sampling time and sample space exhibited a stable system model. The results of the Kalman filtering were a realistic sea state estimate with a minimum error at the locations in the surrounding of the measurements.
- ItemOpen AccessDesign and construction of a vibration data logging prototype board for overland conveyor belts(2006) Verrinder, Robyn A; Tapson, JonathanOverland conveyor belt systems form a vital part of modern transportation systems in the mining and mineral processing industries. It is vital that the system is well maintained in order to minimise system downtime and maximise profit. The conveyor belt is the single most expensive item in the system. It must be monitored to pick up potential problems before they cause belt failure. The majority of conveyor belt monitoring methods identify belt failure events rather than belt failure causes. The purpose of this project was to research and design a belt condition monitoring board which could be physically embedded in the conveyor belt. This would then be used to monitor the condition of the conveyor idlers whose failure can result in major system damage. The venture was split into two areas of research: the design of a vibration data logging board and the design of a power generation system. The thesis focused on the design of a DSP vibration data logging prototype board, while S.A. Williams investigated the design of a power generation system.
- ItemOpen AccessLocalisation and navigation in GPS-denied environments using RFID tags(2014) James, Sisa; Verrinder, Robyn A; Sabatta, Deon; Shahdi, AliThis dissertation addresses the autonomous localisation and navigation problem in the context of an underground mining environment. This kind of environment has little or no features as well as no access to GPS or stationary towers, which are usually used for navigation. In addition dust and debris may hinder optical methods for ranging. This study looks at the feasibility of using randomly distributed RFID tags to autonomously navigate in this environment. Clustering of observed tags are used for localisation, subsequently value iteration is used to navigate to a defined goal. Results are presented, concluding that it is feasible to localise and navigate using only RFID tags, in simulation. Localisation feasibility is also confirmed by experimental measurements.
- ItemOpen AccessSea state estimation from inertial platform data for real-time ocean wave prediction(2018) Gwatiringa, Tinashe G; Boje, Edward; Verrinder, Robyn AOcean observation is vital in understanding how the oceans contribute toward climate change and other effects. This is one of many undertakings requiring a persistent presence in the oceans. These maritime activities are mainly carried out on large research vessels chartered for weeks at a time, which can be extremely costly. In addition, the data obtained when using these vessels are only short snapshots of the continual processes that occur. Recently, there has been a drive toward using Unmanned Surface Vehicles (USVs) and Unmanned Underwater Vehicles (UUVs), which can be deployed at a fraction of the cost, and provide greatly improved spatio-temporal data. The wave glider (WG) is one such autonomous marine robot used for persistent ocean research and other maritime activities, and forms the focus of this study. The WG is a low power USV/UUV hybrid that harnesses wave energy for propulsion, and has a small solar- and battery-powered thruster, and a rudder for steering. Due to effects of waves, currents, and other disturbances, the platform tends to veer off its desired path. Additionally, local sea state information is not taken into consideration while manoeuvring, hence energy extraction from ocean waves is not optimal. More sophisticated navigation algorithms operating on a per-wave strategy may improve accuracy along a specified path and maximise the energy uptake from the waves. To realise these improvements requires prediction of local wave behaviour. If one can predict what the wave field will be a short time in the future, then possible control action can be taken to efficiently navigate in the environment. Inertial measurements and wave modelling have been used to improve localisation of the WG platform directly, and predict the platform’s velocity. However there is limited work in the context of WG navigation. Hence the problem this dissertation aims to solve is the estimation and subsequent prediction of local wave behaviour. This work proposes a novel approach to estimate the sea state and hence predict short-term, local wave behaviour from inertial measurements on a slow-moving marine platform such as the WG. A Kalman filtering strategy consisting of a phase-locked loop and filter based sea state estimator is used to generate local height and angle of arrival estimates. This method offers an improvement over existing Fast Fourier Transform methods as it does not require long time series data to produce results, and enables the prediction of wave behaviour a short time into the future. The ideas are tested in simulation by generating wind waves using ocean wave models such as the Pierson Moskowitz model, and dynamic a dynamic model of the WG platform. In addition, a small scale lab experiment is carried out to verify the performance of the sea-state estimator developed. Preliminary results obtained indicate that relative wave height can be estimated on-board a marine platform, using only inertial sensors.