Dr Jianguo Jack Wang was appointed as a Chancellor's Postdoctoral Research Fellow with the ARC Centre of Excellence for Autonomous Systems (CAS) in UTS early 2009. Currently he is a lecturer with the School of Civil and Environmental Engineering. He received his B.Sc. in Physics from Nanjing University, M.Sc. in Electrical and Information Engineering from The University of Sydney (USyd), and PhD in Goematics from The University of New South Wales (UNSW).
Dr Wang was awarded China Scholarship Council research fellowship in 1997 and came to Austraia as a visiting scholar in USyd. From 1999 to 2008, he studied and worked at USyd and UNSW as a postgraduate student and research associate. He also served as a research fellow, senior engineer and project manager overseas and in Australia. With more than 20 years of broad experience in academic and industry, he is continuously developing his multi-discipline researches in sensor fusion for surveying, navigation and perception; robotics and intelligent systems; environment friendly transportation and housing; GNSS, IMU, Vision and Laser sensors modelling and data fusion etc.
Dr Wang has published over 50 refereed papers and research reports in above fields, and successfully supervised about ten PhD and Master students. He is the peer reviewer for prestigious journals and conferences, such as IEEE Transactions on Intelligent Transportation Systems, IET Radar, Sonar & Navigation, IEEE Robotics and Automation Magazine, Elsevier Pattern Recognition Letters, IEEE International Conference on Robotics and Automation (ICRA) and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) etc.
As a Lecturer with Chancellor's Postdoctoral Research Fellow experience, and Core Member of Centre for Built Infrastructure Research (CBIR), Centre for Autonomous Systems (CAS) and Centre for Intelligent Mechatronic Systems (CIMS), Dr. Wang has expertise in several research areas with recognised research outcomes. His current research activities include ITS (Intelligent Transportation System), GPS, INS (Inertial Navigation Systems), sensor fusion for navigation, mapping and perception; robotics and construction automation; environment friendly transportation and housing etc.
Dr. Wang has been awarded the Michael Richey Medal for the best paper of 2014 in The Journal of Navigation.
Can supervise: YES
- Sensor fusion for navigation, mapping and perception
- GPS, pseudolite, INS, IMU, camera and laser etc. sensors modelling and integration
- Robotics and intelligent systems
- Image processing and pattern recognition
- Construction automation and engineering surveying
- Intelligent transportation systems (ITS)
- Environment friendly transportation and housing
- No destructive testing (NDT)
- Introduction to Civil Engineering (48310)
- Geographic Information Systems (49257)
- Engineering Computations (48221)
- Engineering Capstone Projects
- Engineering ReserchPrjects
- Higher Degree Resarch Projects
Cao, D, Hong, GUANG & Wang, JACK 2018, 'Chemical heat storage for saving the exhaust gas energy in a spark ignition engine', Journal of Clean Energy Technologies (JOCET), vol. 6, no. 1, pp. 41-46.View/Download from: UTS OPUS or Publisher's site
This study was aimed to develop a chemical heat storage system using magnesium hydroxide (Mg(OH)2) and its dehydration and hydration reactions to recover the energy wasted in internal combustion engines (IC engine). The thermal energy of exhaust gas will be stored in the dehydration of Mg(OH)2 to become MgO and H2O, and to release in the hydration of MgO. Experiments were conducted on a 6-cylinder spark ignition engine to estimate the amount of energy loss in the exhaust gas and the reactor efficiency in the dehydration process. The stored heat used to heat fresh air from the ambient temperature to more convenient temperature. Results of the preliminary investigation show that the proposed chemical heat storage system is feasible to recover approximately 5.8 % of the heat loss and the temperature of the air is from 275.5 K to 305.4 K (with the ambient temperature is from 253 K to 283 K and the water vapor pressure is 47kPa).
Banihashemi, S, Ding, G & Wang, J 2017, 'Developing a Hybrid Model of Prediction and Classification Algorithms for Building Energy Consumption', Energy Procedia, vol. 110, pp. 371-376.View/Download from: UTS OPUS or Publisher's site
© 2017 The Authors. Artificial intelligence algorithms have been applied separately or integrally for prediction, classification or optimization of buildings energy consumption. However, there is a salient gap in the literature on the investigation of hybrid objective function development for energy optimization problems including qualitative and quantitative datasets in their constructs. To tackle with this challenge, this paper presents a hybrid objective function of machine learning algorithms in optimizing energy consumption of residential buildings through considering both continuous and discrete parameters of energy simultaneously. To do this, a comprehensive dataset including significant parameters of building envelop, building design layout and HVAC was established, Artificial Neural Network as a prediction and Decision Tree as a classification algorithm were employed via cross-training ensemble equation to create the hybrid function and the model was finally validated via the weighted average of the error decomposed for the performance. The developed model could effectively enhance the accuracy of the objective functions used in the building energy prediction and optimization problems. Furthermore, the results of this novel approach resolved the inclusion issue of both continuous and discrete parameters of energy in a unified objective function without threatening the integrity and consistency of the building energy datasets.
Zhang, Y, Xiong, R, Zhao, Y & Wang, J 2015, 'Real-Time Spin Estimation of Ping-Pong Ball Using Its Natural Brand', IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, vol. 64, no. 8, pp. 2280-2290.View/Download from: Publisher's site
Zhao, Y, Zhang, Y, Xiong, R & Wang, J 2015, 'Optimal State Estimation of Spinning Ping-Pong Ball Using Continuous Motion Model', IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, vol. 64, no. 8, pp. 2208-2216.View/Download from: Publisher's site
Liu, W, Wang, J, Wang, J, Ding, W & Almagbile, A 2011, 'Measurable Realistic Image-based 3D Mapping', Archives of Photogrammetry, Cartography and Remote Sensing, vol. 22, pp. 297-310.View/Download from: UTS OPUS
This paper proposes and demonstrates a 3D map concept that is realistic and image-based, that enables geometric measurements and geo-location services. Additionally, image-based 3D maps provide more detailed information of the real world than 3D model-based maps. The image-based 3D maps use geo-referenced stereo images or panoramic images. The geometric relationships between objects in the images can be resolved from the geometric model of stereo images. The panoramic function makes 3D maps more interactive with users but also creates an interesting immersive circumstance. Actually, unmeasurable image-based 3D maps already exist, such as Google street view, but only provide virtual experiences in terms of photos. The topographic and terrain attributes, such as shapes and heights though are omitted. This paper also discusses the potential for using a low cost land Mobile Mapping System (MMS) to implement realistic image 3D mapping, and evaluates the positioning accuracy that a measureable realistic image-based (MRI) system can produce. The major contribution here is the implementation of measurable images on 3D maps to obtain various measurements from real scenes.
Wang, J 2007, 'Adaptive Tropospheric Delay Modelling in GPS/INS/Pseudolite Integration for Airborne Surveying', Journal of GPS, vol. 6, no. 2, pp. 142-148.
Integrated GPS/INS systems have been used for geo-referencing airborne surveying and mapping platforms. However, due to the limited constellation of GPS satellites and their geometric distribution, the accuracy of such integraed systems cannot meet the requirements of precise airborne surveying. This problem can be addressed by including additional GPS-like ranging signals transmitted from the ground-based pseudolites (PLs). As GPS measurement geometry can be strengthened dramatically by the PL augmentation, systems accuracy and reliability can be improved, especially in the vertical component. Nevertheless, some challenges exist for PLs augmentation. As PLs are relatively close to the receivers, the unit vectors from a PL to reference and rover receivers can be significantly different. PL tropospheric delay modelling errors cannot be effectively mitigated in differencing procedure. Furthermore, PL signals propagate through the lower troposphere, where it is very difficult to accurately model the signal delay due to temporal and spatial variations of meteorological parameters. An adaptive PL tropospheric delay modelling method is developed to reduce modelling error by estimating meteorological parameters in a model. The performance of this method is evaluated with field test data. The testing has shown that the PL tropospheric delay modelling error can be effectively mitigated by the proposed method.
Wang, J 2005, 'Tropospheric Delay Estimation for Pseudolite Positioning', Journal of GPS, vol. 4, no. 1-2, pp. 106-112.
Pseudolites, ground-based GPS signal transmitters, can significantly enhance the GPS satellite geometry or can even be an independent positioning system. However, as pseudolites are very close to the receivers, error effects are different from the traditional GPS and should be considered and modeled in a different way. Tropospheric delay is one of the largest error sources of pseudolite positioning, as pseudolite signal propagates through the lower troposphere which is very difficult to be modeled due to spatial variations in atmosphere. The objective of this research is to analyse pseudolite tropospheric delay modelling methods and to select the optimal tropospheric delay models for different applications. Several methods to estimate the tropospheric delay for pseudolite positioning are introduced and compared. One approach is to utilize single-differenced GPS tropospheric models. Another one is to compute the tropospheric delay as a function of the local refractivity along the pseudolite signal path. The ratio method used for Electronic Distance Measurement (EDM) can also be applied to estimate tropospheric delay. Experiments with simulation and real flight test data are conducted in this study to investigate the proposed methods. The advantages and limitations of each method are analysed. The mode defined by RTCA and its modification are suitable for a low elevation and short range application, such as LAAS and local ground based applications. Models derived from single-differenced NMF and Saastamoinen models perform well in long range and high elevation but have big bias in low elevation. And the model derived from the Hopfield model performs relatively well in all the range and elevation.
Wang, J 2004, 'Pseudolite Augmentation for GPS Aided Aerial Photogrammetry: An Analysis of Systematic Errors.', Geomatics Research Australasia, vol. 81, pp. 30-44.
GPS has been widely used as a geo-referencing tool in aerial surveying. However, the accuracy and availability of GPS positioning cannot meet the stringent requirements of large-scale photogrammetry. Ground-based pseudolites can strengthen measurement geometry for GPS based airborne geo-referencing systems. As a result, positioning accuracy and reliability can be improved, especially in the vertical component. However, as pseudolites are comparatively close to receivers, some challenging issues in systematic error analyses and modeling need to be further investigated. In this paper, the major systematic errors related to pseudolites, such as tropospheric delay, multipath and pseudolite location errors are analysed, and their impacts on the performance of an integrated GPS/Pseudolite airborne geo- reference system are presented.
Wang, J 2004, 'Web-based Resources on GPS/INS Integration', GPS Solutions, vol. 8, no. 3, pp. 189-191.
The integrated GPS/INS system has become an indispensable tool for providing precise and continuous position, velocity and attitude information for many positioning and navigation applications, from surveying and mapping to vehicle navigation, guidance and control. There is an extensive variety of websites that are directly or indirectly related to the technologies and applications of GPS/INS integration. This column presents a selection of the publicly available web-based resources on research-based activities for GPS/INS integration. The selection encompasses those international universities and companies that provide electronic versions of their publications.
Wang, J 2000, 'A Hybrid Method for Unconstrained Handwritten Numeral Recognition by Combining Structural and Neural "Gas" Classifiers', Pattern Recognition Letters, vol. 30, no. 7, pp. 625-635.View/Download from: Publisher's site
Abstract: This paper presents a hybrid method for handwritten numeral recognition that combines two compensatory recognition algorithms by analysing their performance for several aspects. The skeleton-based structural recognition algorithm employed in this method is robust under distortion but sensitive to noise and flaws. On the other hand, the neural network classifier, which uses scaled binary images as features and the neural "gas" model for classification, is relatively immune to noise and flaws but sensitive to distortion. The different performances of the two algorithms for broken, connected or slanted numerals, and the measurement-level decision provided by the neural network are detected and combined with different strategies to develop matching rules for each recognition method. Five combination methods based on performance analysis are developed to meet different requirements. As the two algorithms have fairly compensatory properties, the proposed method improves the recognition rate and reliability by exploiting the advantages and avoiding the weaknesses of each classifier. The experimental results from a large set of data show the efficiency and robustness of the proposed method.
Abstract: Broken characters always create problems in handwriting recognition systems, especially those using boundary and/or skeleton information. This paper presents a macrostructure analysis (MSA) mending method based on skeleton and boundary information and an MSA that investigates the stroke tending direction and other properties of handwritings. A new skeleton end extension algorithm is introduced, which compensates the defectiveness of the skeletonization algorithm and obtains a satisfactory skeleton. When combined with suitable parameters, improved performance from a handwriting classifier is achieved. The experimental results from over 13000 numerals show the efficiency and robustness of the proposed method, raising recognition rates by over 10% for broken handwritten digits, from 74.8% to 86.4%.
Wang, JJ, Gowripalan, N, Li, J & Nguyen, VV 2016, 'Close-range photogrammetry for accurate deformation distribution measurement', Mechanics of Structures and Materials: Advancements and Challenges - Proceedings of the 24th Australasian Conference on the Mechanics of Structures and Materials, ACMSM24 2016, Australian Conference on the Mechanics of Structures and Materials, Taylor and Francis, Perth, Australia, pp. 793-799.View/Download from: UTS OPUS
© 2017 Taylor & Francis Group, London. This paper introduces a methodology for improving the accuracy of Deformation Distribution Measurement (DDM) using close-range photogrammetry. After reviewing various algorithms for 2D Digital Image Correlation (DIC), Zero-Normalized Cross-Correlation (ZNCC) is selected for deformation measurement. The impact of several other factors on DIC measurement accuracy has been investigated, including the type of imaging sensors, the contrast and pattern of a specimen, and searching window size. Optimal option of these factors is proposed. The technique is utilized in the experiment of applying static loading on a replica of a concrete structural component used for Sydney Harbour Bridge. Test results presented in the paper include DIC measurements and validation data from conventional sensors.
Banihashemi Namini, SS, Ding, GKC & Wang, J 2016, 'Identification of BIM-Compatible Variables for Energy Optimization of Residential Buildings: A Delphi Study', AUBEA 2016 The 40th Australasian Universities Building Education Association Conference, Australian Universities Building Education Association Annual Conference, Central Queensland University, Cairns, Australia, pp. 281-291.View/Download from: UTS OPUS
It is believed that drawing an applicable, relevant and coherent batch of variables is a fundamental tenet in the success of having an integrated BIM-based energy optimisation but in order to achieve a high level of usefulness, these variables need to be refined and prioritised. Thus, this paper is to investigate BIM compatible variables which are of top priorities for energy optimisation of residential buildings in the design stage. A sequential exploratory research was conducted to find out the most relevant and significant variables that have a high impact on the energy consumption of residential buildings. A pool including more than 30 variables was established and refined through running Delphi approach with energy and BIM experts to reach the final list of prioritized variables. Conducting a three-round Delphi enabled authors to obtain more meticulous results via a consensus agreement among the respondents on the top 13 variables through lenses of BIM compatibility, applicability to optimization and design stage.
Al-Muhsen, N, Wang, J & Hong, G 2016, 'Investigation to Combustion and Emission Characteristics of the Dual Ethanol Injection Spark Ignition Engine', 20th Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Society, Perth, AU, pp. 1-4.View/Download from: UTS OPUS
Ethanol fuel, as a bioproduct with greater octane number, combustion speed and latent heat of vaporization, has become a common choice as an additive and/or an alternative option to gasoline fuel in the spark ignition engines. In order to fully utilize ethanol fuel properties to improve engine performance, a new injection strategy, ethanol port injection plus ethanol direct injection (EDI), has been in development. Work reported in this paper aimed to investigate, experimentally, the effect of ethanol fuel and dual ethanol injection strategy on engine performance, combustion and emissions characteristics at two engine loads and optimized spark timing. The results of both engine loads, light and medium, demonstrated that the indicated mean effective pressure (IMEP) was significantly improved over all dual ethanol injection strategy compared to GPI. The maximum improvement was 3.3485% and 4.357% at light and medium engine loads respectively. The improvement was mainly due to the reduced combustion duration (θ10-90%) which was reduced by 8.15CAD at light load and 4.28CAD at medium load compared to GPI. However, at higher EDI percentages, the over cooling effect and poor mixture quality adversely affected the combustion quality. The indicated specific nitric oxide emission was considerably reduced, at 100% of EDI, by up to 55.1% and 58.46% at light and medium loads respectively. Nevertheless, because of poor mixture quality and high wall wetting, the indicated specific hydrocarbon and the indicated specific carbon monoxide were raised with the increase of EDI percentage. Regarding the effect of spark timing, the dual ethanol injection strategy improved the IMEP significantly at the maximum IMEP spark timing.
Cao, D, Hong, G & Wang, J 2016, 'Preliminary investigation to the feasibility of chemical heat storage for saving the exhaust gas energy in a spark ignition engine', Website proceedings of the 20th Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Conference, The 20th Australasian Fluid Mechanics Conference, Perth, Australia, pp. 1-4.View/Download from: UTS OPUS
Heat storage has become more important because it utilizes the wasted energy to improve the overall efficiency of energy systems. This study was aimed to develop a chemical heat storage system using magnesium hydroxide (Mg(OH)2) and its endothermic and exothermic reactions to recover the thermal energy of the exhaust gas in internal combustion engines. It was proposed that the reactor receives the thermal energy of exhaust gas in the dehydration of Mg(OH)2 to become MgO and H2O, and releases the stored energy in the hydration of MgO. To increase the thermal conductivity of pure Mg(OH)2 for enhancing the reactor's performance, the working material used, EM8 block, is the mixture of Mg(OH)2 and expanded graphite at a ratio of 8:1. Experiments were conducted on a 6-cylinder spark ignition engine (Toyota Aurion 2GR-FE 3.5L) at stoichiometric air/fuel ratios to estimate the amount of energy loss in the exhaust gas. Experimental data of exhaust gas temperature and volume ratios of exhaust gas constitutions were used to calculate the energy rates of each of the exhaust gas constituents and to estimate the reactor efficiency in the dehydration process. Results of the preliminary investigation show that the proposed chemical heat storage system may be feasible to recover approximately 5.8 % of the heat loss in the exhaust gas
Banihashemi Namini, S, Ding, GK & Wang, J 2015, 'Developing an artificial intelligence-based decision making tool for energy optimization of residential buildings in BIM', The Construction, Building and Real Estate Research Conference of the Royal Institution of Chartered Surveyors, The Australasian Universities' Building Educators Association Conference, Australian Universities Building Education Association Annual Conference, Royal Institution of Chartered Surveyors, Sydney, Australia, pp. 1-8.View/Download from: UTS OPUS
In the recent decade, the potential of saving energy by systematic building management is known to be significant and this task should be considered throughout the lifecycle of a building. However, the most effective decisions related to sustainable design of a building facility are made in the feasibility and early design stages. Using building information modelling can expedite this process and provide the opportunity of testing and assessing different design alternatives and materials selection that may impact on energy performance of buildings. Thus, to proactively rectify building performance issues and improve energy efficiency, there is a need for robust methods that can assist with detection, measurement and optimization of energy performance during the early design stage. The main goal for this paper is to study the possibility of interactions between BIM and energy efficient buildings out of application of cutting-edge technologies such as artificial intelligene methods and develop a framework of this interaction as the downstream to establish a better connection among sustainability and information theories as the upstream. Therefore, through this study, a well-established framework that gives a schematic knowledge of BIM applicability in terms of sustainability and energy optimization through utilizing new computational algorithims will be presented.
Wang, J & Luo, X 2013, 'Purposive sample consensus: A paradigm for model fitting with application to visual odometry', Proceedings of the Field and Service Robotics Conference, International Conference on Field and Service Robotics, Springer, Brisbane, Australia, pp. 335-349.View/Download from: UTS OPUS or Publisher's site
© Springer International Publishing Switzerland 2015. ANSAC (random sample consensus) is a robust algorithm for model fitting and outliers' removal, however, it is neither efficient nor reliable enough to meet the requirement of many applications where time and precision is critical. Various algorithms have been developed to improve its performance for model fitting. A new algorithm named PURSAC (purposive sample consensus) is introduced in this paper, which has three major steps to address the limitations of RANSAC and its variants. Firstly, instead of assuming all the samples have a same probability to be inliers, PURSAC seeks their differences and purposively selects sample sets. Secondly, as sampling noise always exists; the selection is also according to the sensitivity analysis of a model against the noise. The final step is to apply a local optimization for further improving its model fitting performance. Tests show that PURSAC can achieve very high model fitting certainty with a small number of iterations. Two cases are investigated for PURSAC implementation. It is applied to line fitting to explain its principles, and then to feature based visual odometry, which requires efficient, robust and precise model fitting. Experimental results demonstrate that PURSAC improves the accuracy and efficiency of fundamental matrix estimation dramatically, resulting in a precise and fast visual odometry.
Sinha, A & Wang, JJ 2014, 'An implementation of the path integrator mechanism of head direction cells for bio-mimetic navigation', 2014 International Joint Conference on Neural Networks (IJCNN), IEEE International Joint Conference on Neural Networks, IEEE, Beijing, pp. 1984-1991.View/Download from: UTS OPUS or Publisher's site
Head direction cells are thought to be an integral part of the neural navigation system. These cells track the agent's current head direction irrespective of the host's location. In doing so, they process a combination of inputs: angular velocity and visual inputs are major effectors; to correctly encode the agent's current heading. There are close to fifteen models of head direction cell systems found in literature today. Very few of these models have been implemented for bio-mimetic navigation in robots. In this paper, we describe an implementation of the head direction cell system on the robot operating system (ROS) robotic platform as a first step towards a bio-mimetic navigation system for Willow Garage's personal robot 2 (PR2) robot.
Sinha, A & Wang, JJ 2014, 'Bio-mimetic Path Integration Using a Self Organizing Population of Grid Cells', Artificial Neural Networks and Machine Learning – ICANN 2014, International Conference on Artificial Neural Networks, Springer International Publishing, Hamburg, Germany, pp. 675-682.View/Download from: UTS OPUS or Publisher's site
Grid cells in the dorsocaudal medial entorhinal cortex (dMEC) of the rat provide a metric representation of the animal's local environment. The collective firing patterns in a network of grid cells forms a triangular mesh that accurately tracks the location of the animal. The activity of a grid cell network, similar to head direction cells, displays path integration characteristics. Classical robotics use path integrators in the form of inertial navigation systems to track spatial information of an agent as well. In this paper, we describe an implementation of a network of grid cells as a dead reckoning system for the PR2 robot.
Zhang, Y, Zhao, Y, Xiong, R, Wang, Y, Wang, JJ & Chu, J 2014, 'Spin Observation and Trajectory Prediction of a Ping-Pong Ball', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Hong Kong, China, pp. 4108-4114.View/Download from: UTS OPUS or Publisher's site
For ping-pong playing robots, observing a ball and
predicting a ball's trajectory accurately in real-time is essential.
However, most existing vision systems can only provide ball's
position observation, and do not take into consideration the
spin of the ball, which is very important in competitions. This
paper proposes a way to observe and estimate ball's spin in
real-time, and achieve an accurate prediction. Based on the
fact that a spinning ball's motion can be separated into global
movement and spinning respect to its center, we construct an
integrated vision system to observe the two motions separately.
With a pan-tilt vision system, the spinning motion is observed
through recognizing the position of the brand on the ball and
restoring the 3D pose of the ball. Then the spin state is estimated
with the method of plane fitting on current and historical
observations. With both position and spin information, accurate
state estimation and trajectory prediction are realized via
Extended Kalman Filter(EKF). Experimental results show the
effectiveness and accuracy of the proposed method.
Li, Y, Wang, J & Kong, X 2013, 'Zero velocity update with stepwise smoothing for inertial pedestrian navigation', International Global Navigation Satellite Systems Society 2013 Symposium Proceedings, International Global Navigation Satellite Systems Society, Menay Pty Ltd, Australia, Surfers Paradise, Australia, pp. 1-10.View/Download from: UTS OPUS
Zero velocity update (ZUPT) is an effective way to correct low cost inertial measurement unit (IMU) errors when it is foot-mounted for pedestrian navigation. The stance phase in steps provides zero velocity measurement for inertial sensor error correction. As the errors of IMU estimated position and velocity grow rapidly with time between each correction, ZUPT applied at each step leads to sharp corrections and discontinuities in the estimated trajectory. For motion analysis and visualization, these large corrections are undesirable. Consequently, the implementation of smoothing for ZUPT-aided INS is considered to eliminate the sharp corrections. In this paper, we propose a closed loop Rauch-Tung-Striebel (RTS) smoother using a 24 error states extended Kalman filter (EKF) implement on our previous pedestrian navigation systems. Unlike common RTS smoother which operates as off-line processing mode, a near-real-time stepwise smoother is implemented to eliminate the sharp corrections over the steps. The impact of the near real-time smoothing filter for different step manners (walk, run and climb stairs) combined with the Constant Velocity Update (CUPT) concept we proposed previously is illustrated and analysed. Experimental results show that the proposed method can dramatically improve pedestrian navigation smoothness.
Li, Y & Wang, J 2012, 'A robust pedestrian navigation algorithm with low cost IMU', Int. Conf. on Indoor Positioning and Indoor Navigation (IPIN 2012), International Conference on Indoor Positioning and Indoor Navigation (IPIN), The University of New South Wales, University of New South Wales, Sydney, Australia, pp. 1-7.View/Download from: UTS OPUS or Publisher's site
The 3rd International Conference on Indoor Positioning and Indoor Navigation (IPIN) will take place on 13-15th November, 2012 at the University of New South Wales, Sydney, Australia.
Li, Y, Luo, X, Ren, X & Wang, J 2012, 'A Robust Humanoid Robot Navigation Algorithm with ZUPT', IEEE International Conference on Mechatronics and Automation, IEEE International Conference on Mechatronics and Automation, IEEE, Chengdu,China, pp. 505-510.View/Download from: UTS OPUS or Publisher's site
this paper discusses algorithmic concepts, design and testing of a pedestrian dead reckoning (PDR) navigation system based on a low-cost inertial measurement unit (IMU) attached to a userâs shoe. The algorithm uses the technique known as âZero Velocity Updateâ (ZUPT) and Kalman Filter consists of 24 error states to reduce IMU errors. We propose a novel dynamic and more robust algorithm to detect the stance phases during walking. The system works well in both 2D (2-dimensional) and 3D environments. Test results show that its horizontal positioning errors are always below 0.3% of the total travelled distance, and the vertical errors are below 0.7%, even on 3D terrain. These results reach the highest position accuracy in available literature.
Li, Y, Wang, J, Xiao, S & Luo, X 2012, 'Dead Reckoning Navigation with Constant Velocity Update (CUPT)', The 12th International Conference on Control, Automation, Robotics and Vision (ICARCV2012), International Conference on Control, Automation, Robotics and Vision, IEEE, Guangzhou, China, pp. 160-165.View/Download from: UTS OPUS or Publisher's site
ICARCV focuses on both theory and applications mainly covering the topics of control, automation, robotics and vision. In addition to the technical sessions, there will be invited sessions, panel sessions and keynote addresses. ICARCV is a ERA ranking A conference.
Luo, X, Li, Y, Ren, X & Wang, J 2012, 'Automatic Road Surface Profiling with Sensors Fusion', 2012 12th International Conference on Control, Automation, Robotics & Vision, International Conference on Control, Automation, Robotics and Vision, IEEE, Guangzhou, China, pp. 608-613.View/Download from: UTS OPUS or Publisher's site
This paper addresses the issue of automatically profiling the road surface based on sensor fusion. Road surface profiling in this research paper includes road boundary detection, white line detection and lane division. We propose an approach to perform automatic and robust road surface profiling with the fusion of the following sensors: LADAR (Laser Detection and Ranging), GPS (Global Positioning System), INS (Inertial Navigation System), cameras and an odometer. The LADAR is the most important in our research since we propose a new technique that utilizes laser remission to detect white lines. A prototype system has also been developed for testing with the capability of converting profiling results into video files for easy reference and management. The system is able to work under severe weather and light condition, and profiling all lanes within road boundary at one run. Experimental results on a wide variety of roads have demonstrated the effectiveness of the proposed system.
Luo, X, Ren, X, Li, Y & Wang, J 2012, 'Mobile Surveying System for Road Assets Monitoring and Management', 7th IEEE Conference on Industrial Electronics and Applications (ICIEA 2012), IEEE Conference on Industrial Electronics and Applications, IEEE, Singapore, pp. 1688-1693.View/Download from: UTS OPUS or Publisher's site
ICIEA is a premier conference, providing an excellent forum for scientists, researchers, engineers and industrial practitioners throughout the world to present and discuss the latest technology advancement in Industrial Electronics. The Conference is organized by IEEE Industrial Electronics (IE) Chapter of Singapore Section, with ERA Ranking A. Our paper is accepted for oral presentation.
Ahmad, A, Huang, S, Wang, J & Dissanayake, G 2012, 'A new state vector and a map joining algorithm for range-only SLAM', International Conference on Control, Automation, Robotics & Vision, International Conference on Control, Automation, Robotics and Vision, IEEE, Guangzhou, China, pp. 1024-1029.View/Download from: UTS OPUS or Publisher's site
This paper considers the simultaneous localization and mapping (SLAM) problem where the range-only sensor is used. Landmark initialization is a critical issue in range-only SLAM due to the lack of bearing information from the robot to the landmarks. A new state vector is proposed to be used in solving the range-only SLAM. In the new state vector, the landmark position is represented in different ways under different situations. This new representation avoids the need of multiple hypotheses on the landmark positions implemented in most of the existing range-only SLAM algorithms. Simulation and experimental results demonstrate the effectiveness of the new range-only SLAM algorithm using the new state vector within the least squares framework.
Zhuang, Y, Hong, G & Wang, J 2012, 'Preliminary investigation to combustion in a SI engine with direct ethanol injection and port gasoline injection (EDI+GPI)', Proceedings of the Eighteenth AUSTRALASIAN FLUID MECHANICS CONFERENCE, Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Society, Launceston, Tasmania, Australia, pp. 1-4.View/Download from: UTS OPUS
Ethanol fuel, as a renewable fuel can play an important role in addressing the critical issue of energy resources if it is used in a proper way. Ethanol direct injection plus gasoline port injection (EDI+GPI) is such a new way to enable substantial improvement in engine efficiency and emission reduction in spark ignition engines. This paper reports our preliminary investigation to the combustion and emissions in this new dual fuel injection system. Experiments were conducted on a single-cylinder spark ignition engine equipped with EDI+GPI. In the experiments, the ethanol/gasoline volumetric percentage (EVP) was varied from 0% (gasoline fuel only) to 71%. Mass burnt fraction and indicated mean effective pressure (IMEP) were calculated from the measured cylinder pressure for analysing the combustion process. The variance of IMEP, reduced with the increased EVP, showed that the combustion stability was improved by the direct injection of ethanol fuel. The effect of EVP on initial, early and major combustion time periods showed that ethanol fuelâs higher combustion velocity and low ignition energy might contribute to accelerating the flame propagating, shortening the combustion periods and reducing the combustion temperature when EVP was less than 48%. However further increase of EVP when it was over 48% resulted in a negative effect on combustion which might be caused by the ethanol fuelâs over cooling effect. Hydrocarbon and carbon monoxide emission increased and nitric oxide emission decreased with the increase of EVP.
Zhuang, Y, Wang, J & Hong, G 2012, 'A single cylinder research engine for investigating combustion of direct ethanol injection and port gasoline injection', Proceedings of the 18th Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Society, Launceston, Tasmania, Australia, pp. 1-4.View/Download from: UTS OPUS
Ethanol has been used as a renewable fuel in internal combustion (IC) engines. However, the existing method of blending gasoline and ethanol fuels does not take the advantages of ethanol fuel, such as its high Octane number and great latent heat of vaporization, to increase the engine compression ratio and consequently the thermal efficiency. Ethanol direct injection plus gasoline port injection (EDI+GPI) is a new technology for using ethanol fuel more effectively and efficiently in IC engine. To experimentally investigate this new technique, a research engine has been developed by modifying a commercial product representing the cylinder capacity of a down sized passenger car engine. In the development of this research engine, two major tasks were addressed: the two separate fuel systems and the electronic control unit (ECU). The operation of both fuel systems including the high pressure pump and the common rail fuel pressure are electronically controlled. The ECU also controls the throttle position and fuel flow rates in an open loop to provide the flexibility of manual adjustments of engine speed, load and lambda. Sample results are reported to show that the developed engine system has met the basic requirements of experiments in this investigation.
Ren, X, Luo, X & Wang, J 2011, 'Automatic Road Clearance Surveying with Sensor Fusion', Proceedings of Australasian Conference on Robotics and Automation 2011 (ACRA2011), Australasian Conference on Robotics and Automation, The Australian Robotics and Automation Association Inc. (ARAA), Monash University, Melbourne Australia, pp. 1-8.View/Download from: UTS OPUS
This paper introduces an automatic road clearance surveying (ARCS) method based on sensor fusion. Equipped with laser measurement system (LMS), camera and proprioceptive sensors (IMU and Odometer), this system is very efficient with improved personal safety. The LMS sensors measure surroundings by collecting range and remission data. Range data is processed to build up 3D model of surveyed objectives with position and attitude information from the proprioceptive sensors. Remission data is used for extracting traffic lanes. The lowest points detected within each lane are considered to be the lanesâ clearance, and marked on the 3D model. Experimental results of a vehicle mounted prototype demonstrate its performance for automatic road clearance surveying.
Ahmad, A, Huang, S, Wang, J & Dissanayake, G 2011, 'A new state vector for range-only SLAM', Proceedings of the 2011 Chinese Control and Decision Conference, Chinese Control and Decision Conference, IEEE, Mianyang, Sichuan, China, pp. 3413-3418.View/Download from: UTS OPUS or Publisher's site
This paper considers the simultaneous localization and mapping (SLAM) problem where the range-only sensor is used. Landmark initialization is a critical issue in rangeonly SLAM due to the lack of bearing information from the robot to the landmarks. A new state vector is proposed to be used in solving the range-only SLAM. In the new state vector, the landmark position is represented in different ways under different situations. This new representation avoids the need of multiple hypotheses on the landmark positions implemented in most of the existing range-only SLAM algorithms. Simulation and experimental results demonstrate the effectiveness of the new range-only SLAM algorithm using the new state vector within the least squares framework.
Zhao, L, Huang, S, Yan, L, Wang, J, Hu, G & Dissanayake, G 2010, 'Large-Scale Monocular SLAM by Local Bundle Adjustment and Map Joining', 2010 International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Singapore, pp. 431-436.View/Download from: UTS OPUS or Publisher's site
This paper first demonstrates an interesting property of bundle adjustment (BA), âscale drift correctionâ. Here âscale drift correctionâ means that BA can converge to the correct solution (up to a scale) even if the initial values of the camera pose translations and point feature positions are calculated using very different scale factors. This property together with other properties of BA makes it the best approach for monocular Simultaneous Localization and Mapping (SLAM), without considering the computational complexity. This naturally leads to the idea of using local BA and map joining to solve large-scale monocular SLAM problem, which is proposed in this paper. The local maps are built through Scale-Invariant Feature Transform (SIFT) for feature detection and matching, random sample consensus (RANSAC) paradigm at different levels for robust outlier removal, and BA for optimization. To reduce the computational cost of the large-scale map building, the features in each local map are judiciously selected and then the local maps are combined using a recently developed 3D map joining algorithm. The proposed large-scale monocular SLAM algorithm is evaluated using a publicly available dataset with centimeter-level ground truth.
Wang, J 2009, 'Vision Aided GPS/INS System for Robust Land Vehicle Navigation', Proceedings of the 22nd Int. Tech. Meeting of the Satellite Division of the U.S. Inst. of Navigation, 22nd Int. Tech. Meeting of the Satellite Division of the U.S. Inst. of Navigation, U.S. Inst. of Navigation, Savannah International Convention Center, Savannah, GA, US, pp. 600-609.
: This paper introduces a new approach for improving land vehicle navigation by integrating a digital camera with a GNSS receiver and a MEMS INS, to provide seamless robust navigation solutions in urban environment. As a camera has the ability to detect surrounding environment, it can measure its relative position and direction to the surrounding objects. The integration of heterogeneous sensors with very different characters, such as GNSS, INS and image in this approach, can complement each other and provide cost-effective and robust navigation solutions. In the proposed system, INS is selected as the reference navigation sensor as it provides complete navigation solutions without disruptions. The navigation errors caused by its inherent nonlinear and time-varying characteristics can be corrected by the camera and GNSS. Vision based navigation (VBN) is one of the fundamental issues in computer vision and is relatively well developed. In this paper mono vision (MV) based navigation technologies are merged with GNSS and INS measurement, termed as GNSS/INS/MV (GIMV) integration. VBN is at the core of proposed robust navigation system, in which a relative range scale factor is estimated by continuously applying structure-from-motion in the MV navigation. Due to the complexity of multi-sensor integration, it needs an optimal sensor fusion framework with reliable system design, modeling and quality control procedures. The proposed sensor fusion method consists of two local and one master data fusion units, based on extended Kalman filter and fuzzy logic. It takes the advantages of federate architecture, and can select using either GNSS or VBN navigation solutions for INS correction according to their quality. GNSS/INS integration is the mainstream for navigation when the vehicle travels in an open area with good GNSS signal. At the same time, the modeling parameters of INS and camera are estimated. When the system is navigating in areas with weak GNSS signals, such as...
Wang, J, Hu, G, Huang, S & Dissanayake, G 2009, '3D Landmarks Extraction from a Range Imager Data for SLAM', Proceedings of the 2009 Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc., Sydney, Australia, pp. 1-8.View/Download from: UTS OPUS
This paper introduces a new 3D landmark extraction method using the range and intensity images captured by a single range camera. Speeded up robust features (SURF) detection and matching is used to extract and match features from the intensity images. The range image information is used to transfer the selected 2D features into 3D points. The range measurement bias and uncertainty of the range camera are analysed, and their models are developed for improving the range estimation. After outliersâ detection and removal using random sampling consensus (RANSAC), reliable 3D points are obtained. 3D landmarks for imultaneous localisation and mapping (SLAM) are selected from the 3D points considering several factors, such as the uncertainty and geometry of their locations. Because of the availability of the SURF descriptor, the data association in SLAM has been performed using both the geometry and the descriptor information. The proposed method is tested in unstructured indoor environments, where the range camera moves in six degrees of freedom. Experimental results demonstrate the success of the proposed 3D landmark extraction method for SLAM.
Wang, JJ, Kodagoda, S & Dissanayake, G 2009, 'Vision aided GPS/INS system for robust land vehicle navigation', 22nd International Technical Meeting of the Satellite Division of the Institute of Navigation 2009, ION GNSS 2009, pp. 195-204.
This paper introduces a new approach for improving land vehicle navigation by integrating a digital camera with a GNSS receiver and a MEMS INS, to provide seamless robust navigation solutions in urban environment. As a camera has the ability to detect surrounding environment, it can measure its relative position and direction to the surrounding objects. The integration of heterogeneous sensors with very different characters, such as GNSS, INS and image in this approach, can complement each other and provide cost-effective and robust navigation solutions. In the proposed system, INS is selected as the reference navigation sensor as it provides complete navigation solutions without disruptions. The navigation errors caused by its inherent nonlinear and time-varying characteristics can be corrected by the camera and GNSS. Vision based navigation (VBN) is one of the fundamental issues in computer vision and is relatively well developed. In this paper mono vision (MV) based navigation technologies are merged with GNSS and INS measurement, termed as GNSS/INS/MV (GlMV) integration. VBN is at the core of proposed robust navigation system, in which a relative range scale factor is estimated by continuously applying structure-from-motion in the MV navigation. Due to the complexity of multi-sensor integration, it needs an optimal sensor fusion framework with reliable system design, modeling and quality control procedures. The proposed sensor fusion method consists of two local and one master data fusion units, based on extended Kalman filter and fuzzy logic. It takes the advantages of federate architecture, and can select using either GNSS or VBN navigation solutions for PNS correction according to their quality. GNSS/INS integration is the mainstream for navigation when the vehicle travels in an open area with good GNSS signal. At the same time, the modeling parameters of INS and camera are estimated. When the system is navigating in areas with weak GNSS signals, such as u...
Wang, J, Garratt, M, Lambert, A, Wang, JJ, Han, S & Sinclair, D 2008, 'Integration of GPS/INS/VISION sensors to navigate unmanned aerial vehicles', International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, pp. 963-969.
© 2008 International Society for Photogrammetry and Remote Sensing. All rights reserved. This paper presents an integrated GPS/INS/Vision navigation system for Unmanned Aerial Vehicles (UAVs). A CCD (Charge- Coupled Device) video camera and laser rangefinder (LRF) based vision system, combined with inertial sensors, provides the information on the vertical and horizontal movements of the UAV (helicopter) relative to the ground, which is critical for the safety of UAV operations. Two Kalman filers have been designed to operate separately to provide a reliable check on the navigation solutions. When GPS signals are available, the GPS measurements are used to update the error states in the two Kalman filters, in order to estimate the INS sensors, LRF and optic flow modelling errors, and provide redundant navigation solutions. With the corrected measurements from the vision system, the UAV's relative movements relative to the ground are then estimated continuously, even during GPS signal blockages. The modelling strategies and the data fusion procedure for this sensor integration scenario are discussed with some numerical analysis results, demonstrating the potential performance of the proposed triple integration.
Wang, JJ, Ding, W & Wang, J 2007, 'Improving adaptive kalman filter in GPS/SDINS integration with neural network', 20th International Technical Meeting of the Satellite Division of The Institute of Navigation 2007 ION GNSS 2007, pp. 571-578.
Kalman filter (KF) can provide optimal solutions if the system dynamic and measurement models are correctly defined, and the noise statistics for the measurement and system are completely known. The conventional way of determining the covariance matrices of process noise and observation errors relies on analysis of empirical data from each sensor in a system, which is called KF tuning. In practice, however, the process noise and observation errors vary with time and environment, which causes uncertainty in the covariance matrices of process noise and observation errors and results in system performance degradation. Adaptive KF (AKF) has been intensively investigated, which can tune a filter continuously so as to eliminate empirical data analysis and aims to improve filtering performance. The covariance matching technique in AKF uses innovation-based estimation that attempts to make the filter residual covariances consistent with their theoretical covariances estimated with samples. This paper presents a neural network aided AKF based on covariance matching technique, for integrated GPS/INS system. Instead of using a limited window for estimation as conventional AKF, all the previous samples are counted in according to their character using neural network (NN). The covariance matching is conducted then its relation with the corresponding character is mapped with the NN. The adjustment of the AKF is based on both the NN training result and the updated covariance matching result. The purpose of doing so is to eliminate estimation noise, and to keep the selected samples ergodic. The objective of this research is to develop a system that is self-adaptive to the change of operation environment or hardware components, such as the type of INS and system configuration etc. with the help of AKF. The principle of this hybrid method and the NN design are presented. Field test data are processed to evaluate the performance of the proposed method. Different types of INS are te...
Wang, JJ, Wang, J, Sinclair, D & Watts, L 2007, 'Neural network aided Kalman Filtering for integrated GPS/INS geo-referencing platform', International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.
© 2007 International Society for Photogrammetry and Remote Sensing. All rights reserved. Kalman filtering theory plays an important role in integrated GPS/INS georeference system design. A Kalman filter (KF) uses measurement updates to correct system states error and to limit the errors in navigation solutions. However, only when the system dynamic and measurement models are correctly defined, and the noise statistics for the process are completely known, a KF can optimally estimate a system's states. Without measurement updates, a Kalman filter's prediction diverges; therefore the performance of an integrated GPS/INS georeference system may degrade rapidly when GPS signals are unavailable. It is a challenge to deal with this problem in real time though it can be handled in post processing by smoothing methods. This paper presents a neural network (NN) aided Kalman filtering method to improve navigation solutions of integrated GPS/INS georeference system. It is known that the errors inherent to strapdown inertial sensors are affected by the platform manoeuvre and environment conditions etc., which are hard to be modelled precisely. On the other hand, NNs have the capability to map inputoutput relationships of a system without apriori knowledge about them. A properly designed NN is able to learn and extract complex relationships given enough training. Furthermore, it is able to adapt to the change of sensors and dynamic platforms. In the proposed loosely coupled GPS/INS georeference system, an extended KF (EKF) estimates the INS measurement errors, plus position, velocity and attitude errors, and provides precise navigation solutions while GPS signals are available. At the same time, a multi-layer NN is trained to map the vehicle manoeuvre with INS prediction errors during each GPS epoch, which is the input of the EKF. During GPS signal blockages, the NN can be used to predict the INS errors for EKF measurement updates, and in this way to improve navigation soluti...
Wang, JJ, Wang, J, Sinclair, D & Watts, L 2006, 'High-Accuracy Airborne GPS/INS Positioning Augmented by Pseudolite', PROCEEDINGS OF THE 2006 NATIONAL TECHNICAL MEETING OF THE INSTITUTE OF NAVIGATION - NTM 2006, 2006 National Technical Meeting of the Institute-of-Navigation, INST NAVIGATION, Monterey, CA, pp. 515-522.
Wang, JJ 2005, 'Modeling and geometry design for pseudolite augmented airborne DGPS', Proceedings of the 18th International Technical Meeting of the Satellite Division of The Institute of Navigation, ION GNSS 2005, pp. 2076-2082.
Carrier phase DGPS systems have been increasingly used in airborne surveying. However, the accuracy and availability of GPS positioning cannot meet the stringent requirements of large-scale photogrammetry. Ground-based pseudolites can strengthen the measurement geometry for airborne GPS systems, and improve ambiguity resolution. As a result, positioning accuracy and reliability can be improved, especially in the vertical component. In order to effectively augment DGPS aided airborne surveying with pseudolites, carrier phase measurements of pseudolites need to be employed in the positioning process. However, due to the comparatively small separations between pseudolites and receivers, some challenging issues have to be investigated, such as geometry design, nonlinearity, tropospheric delay and pseudolite location errors. Geometry design is extremely important for pseudolite augmented GPS positioning system. Optimally located pseudolite and reference receiver can significantly improve the geometric strength of positioning solutions and thus reduce the effects of nonlinearity and pseudolite location error. The optimal locations of pseudolite and reference receiver are proposed based on analyzing these issues and the simulation results in airborne surveying scenarios. Nonlinearity is a challenging issue in pseudolite augmented DGPS. The nonlinear geometry bias in processing pseudolite measurements can be effectively eliminated by Projected Single Difference strategy, which can also be used in processing GPS measurements to improve the positioning accuracy. Several pseudolite tropospheric delay models are introduced and evaluated, and optimal models corresponding to different applications are proposed. Simulation and real data test results have shown the effectiveness of the proposed methods.
© 1999 IEEE. Many handwritten character recognition systems can achieve a high recognition rate in general, but yield poor accuracy for flawed handwritten characters. This paper presents a new scheme to improve the recognition of flawed handwritten characters using a sequence of connected stroke separations, broken character mending and distorted characters recognition methods associated within a hybrid recognition system. A structural recognition algorithm combined with a neural network classifier is used to test the efficiency of the proposed method for renovating flawed character. Experimental results on a large set of data show the efficiency and robustness of the proposed method for handwritten digits recognition.