• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.798-802
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper, the robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is to use different models (CAD model etc.) known a priori. Also fusion of multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Because voting is a very simple or no model is needed for fusion, voting-based fusion of cues is applied. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters, namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1055-1058
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is the use of different model (CAD model etc.) known a priori. Also fusion or multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Voting-based fusion of cues is adapted. In voting. a very simple or no model is used for fusion. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters. namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.7
• /
• pp.1241-1246
• /
• 2008

The dynamics of mobile robot is nonlinear. To cope with this nonlinearity, many advanced control schemes have been proposed recently. Generally, the advanced control schemes are complicated and not good for the practical real-time control when they are implemented as control programs. So, in this paper, a relatively simple PI controller is proposed and applied to the position control of mobile robot with the adoption of reference trajectory calculation method used for the AUV(Autonomous Underwater Vehicle) control. The proposed PI controller is programmed using LabVIEW which is popular for its graphical programming characteristics. The simulation and experimental results show the feasibility and effectiveness of the proposed PI controller.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.277-282
• /
• 2006

It is well known that Kalman filtering is an optimal real-time data fusion method for GPS/INS integration. However, it has some limitations in terms of stability, adaptability and observability. A Kalman filter can perform optimally only when its dynamic model is correctly defined and the noise statistics for the measurement and process are completely known. It is found that estimated Kalman filter states could be influenced by several factors, including vehicle dynamic variations, filter tuning results, and environment changes, etc., which are difficult to model. Neural networks can map input-output relationships without apriori knowledge about them; hence a proper designed neural network is capable of learning and extracting these complex relationships with enough training. This paper presents a GPS/INS integrated system that combines Kalman filtering and neural network algorithms to improve navigation solutions during GPS outages. An Extended Kalman filter estimates INS measurement errors, plus position, velocity and attitude errors etc. Kalman filter states, and gives precise navigation solutions while GPS signals are available. At the same time, a multi-layer neural network is trained to map the vehicle dynamics with corresponding Kalman filter states, at the same rate of measurement update. After the output of the neural network meets a similarity threshold, it can be used to correct INS measurements when no GPS measurements are available. Selecting suitable inputs and outputs of the neural network is critical for this hybrid method. Detailed analysis unveils that some Kalman filter states are highly correlated with vehicle dynamic variations. The filter states that heavily impact system navigation solutions are selected as the neural network outputs. The principle of this hybrid method and the neural network design are presented. Field test data are processed to evaluate the performance of the proposed method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.6
• /
• pp.951-957
• /
• 2010

An optimal path generation method considering the safety of UGV(Unmanned Ground Vehicle) is proposed and demonstrated through examples. Among various functions of UGV, real-time obstacle avoidance is a key issue to realize realistic scenario in FCS(Future Combat Systems). A two-dimensional narrow corridor environment is considered as a test field. For each step of UGV movement, two objectives are considered: One is to minimize the distance to the target and the other to maximize the distance to the nearest point of an obstacle. A weighted objective function is used in the optimization problem. Equality and inequality constraints are taken to secure the UGV's dynamics and safety. The weighting factors are controlled by a fuzzy controller which is constructed by a fuzzy rule set and membership functions. Simulations are performed for two cases. First the weighting factors are considered as constant values to understand the characteristics of the corresponding solutions and then as variables that are adjusted by the fuzzy controller. The results are satisfactory for realistic situations considered. The proposed optimal path generation with the fuzzy control is expected to be well applicable to real environment.

• International Journal of Automotive Technology
• /
• v.8 no.3
• /
• pp.383-394
• /
• 2007

Due to the clutch's non-linear dynamics, time-delays, external disturbance and parameter uncertainty, the automated clutch is difficult to control precisely during the launch process or automatic mechanical transmission (AMT) vehicles. In this paper, an enhanced fuzzy sliding mode controller (EFSMC) is proposed to control the automated clutch. The sliding and global stability conditions are formulated and analyzed in terms of the Lyapunov full quadratic form. The chattering phenomenon is handled by using a saturation function to replace the pure sign function and fuzzy logic adaptation system in the control law. To meet the real-time requirement of the automated clutch, the region-wise linear technology s adopted to reduce the fuzzy rules of the EFSMC. The simulation results have shown hat the proposed controller can achieve a higher performance with minimum reaching time and smooth control actions. In addition, our data also show that the controller is effective and robust to the parametric variation and external disturbance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.11
• /
• pp.1479-1485
• /
• 2012

The development of a technique for the real-time sensing of a curve section is very important for active rolling-stocks in order to improve the curving performance. However, conventional methods using expensive track inspection equipment or various complex sensors are not practicable to be applied to commercial vehicles. Therefore, we have proposed a new method to estimate the curve radius of a curve section. This method uses the relative displacements occurring between the body and the bogie when the rolling-stock is running on a curve. To verify the validity of this method, we conducted a vehicle dynamics simulation and test using a real vehicle on a test line. The results confirmed the validity of the proposed method. We expect that this method will be effectively applied in studies of active rolling-stocks to increase the curving performance using active control technology.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2002.11a
• /
• pp.163-170
• /
• 2002

Terrain surfaces have to be modeled in very detail and wheel-surface contacting geometry must be well defined in order to obtain proper ground-reaction and friction forces for realistic simulation of off-road vehicles. Delaunay triangulation is one of the most widely used methods in modeling 3-dimensional terrain surfaces, and T-search is a relevant algorithm for searching resulting triangular polygons. The T-search method searches polygons in successive order and may not allow real-time computation of off-road vehicle dynamics if the terrain is modeled with many polygons, depending on the computer performance used in the simulation. In order to accelerate the searching speed of T-search, a terrain database of triangular polygons is modeled in multi-levels by adopting the LOD (Level of Detail) method used in realtime computer graphics. Simulation results show that the new LOD search is effective in shortening the required computing time. The LOD search can be even further accelerated by introducing an NN (Neural Network) algorithm, in the cases where a appropriate range of moving paths can be predicted by cultual information of the simulated terrain, such as lakes, houses, etc.. Numerical tests show that LOD-NN search almost double the speed of the original T-search.

• Journal of Korean Society of Rural Planning
• /
• v.19 no.4
• /
• pp.137-147
• /
• 2013

Most of livestock houses are concentrated in certain area with mass rearing system resulting in rapid spread of infectious diseases such as HPAI (highly pathogenic avian influenza). The livestock-related vehicles which frequently travel between farms could be a major factor for disease spread by means of transmission of airborne aerosol including pathogens. This study was focused on the quantitative measurement of aerosol concentration by field experiment while vehicles were passing through the road. The TSP (total suspended particle) and PM10 (particle matter) were measured using air sampler with teflon filter installed downward the road with consideration of weather forecast and the direction of road. And aerosol spectrometer and video recorders were also used to measure the real-time distribution of aerosol concentration by its size. The results showed that PM2.5 was not considerable for transmission of airborne aerosol from the livestock-related vehicle. The mass generated from the road during the vehicle movement was measured and calculated to 241.4 ${\mu}g/m^3$ by means of the difference between TSP and PM2.5. The dispersion distance was predicted by 79.6 m from the trend curve.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.297-304
• /
• 2015

Recently, the demand for a PRT(Personal Rapid Transit) system based on autonomous navigation is increasing. Accordingly, the applicability investigations of the PRT system on rail tracks or roadways have been widely studied. In the case of unmanned vehicle operations without physical guideways on roadways, to monitor the position of the vehicle in real time is very important for stable, robust and reliable guidance of an autonomous vehicle. The Global Positioning System (GPS) has been commercially used for vehicle positioning. However, it cannot be applied in environments as tunnels or interiors of buildings. The PRT navigation system based on magnetic markers reference sensing that can overcome these environmental restrictions and the vehicle dynamics model for its H/W configuration are presented in this study. In addition, the design of a control S/W dedicated for unmanned operation of a PRT vehicle and its prototype implementation for experimental validation on a pilot network were successfully achieved.