• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.438-446
• /
• 2022

In this paper, we propose an intelligent three-legged landing system that can maintain stability and level even on rough terrain than conventional four-legged landing systems. Conventional landing gear has the limitation that it requires flat terrain for landing. The 3-leg landing system proposed in this paper extends the usable range of the legs and reduces the weight, allowing the quadcopter to operate in various environments. To do this, kinematics determine the joint angles and coordinates of the legs of the two-link structure. Based on the angle value of the quadcopter detected via the IMU sensor, the leg control method that corrects the posture is determined. A force sensor attached to the end of the leg is used to detect contact with the ground. At the moment of contact with the ground, landing control starts according to the value of the IMU sensor. The proposed system verifies its reliability in various environments through an indoor landing test stand. Finally, in an outdoor environment, the quadcopter lands on a 20 degree incline and 20 cm rough terrain after flight. This demonstrates the stability and effectiveness of the 3-leg landing system even on rough terrain compared to the 4-leg landing system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.353-368
• /
• 2023

The four wing unmanned aerial vehicle owns the characteristics of small size, light weight, convenient operation and well stability. But it is easily disturbed by external environmental factors during flight with these disadvantages of short endurance and poor attitude solving ability. For solving these problems, a microprocessor based on STM32 chip is designed and the overall development is completed by the resources such as built-in timer and multi-function mode general-purpose input/output provided by the master micro controller unit, together with radio receiver, attitude meter, barometer, electronic speed control and other devices. The unmanned aerial vehicle can be remotely controlled and send radio waves to its corresponding receiver, control the analog level change of its corresponding channel pins. The master control chip can analyze and process the data to send multiple sets pulse signals of pulse width modulation to each electronic speed control. Then the electronic speed control will transform different pulse signals into different sizes of current value to drive the motor located in each direction of the frame to generate different rotational speed and generate lift force. To control the body of the unmanned aerial vehicle, so as to achieve the operator's requirements for attitude control, the PID controller based on Kalman filter is used to achieve quick response time and control accuracy. Test results show that the design is feasible.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.1-7
• /
• 2023

Mission autonomy system should be embedded on UAV (Unmanned Aerial Vehicle) for mosaic warfare where UAVs autonomously assign tasks to themselves. UxAS (Unmanned x-systems Autonomy Service) proposed by Air Force Research Laboratory is mission autonomy system for unmanned platforms. UxAS has extensible structure composed of numerous module services. However, UxAS can conduct mission autonomy process only when an operator sends an autonomy request. In this paper, We analyze the process of mission autonomy in UxAS, and propose an improved structure of UxAS where mission autonomy process is autonomously triggered by situation awareness service without the request of the operator. The proposed process was validated by simulation.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.30 no.4
• /
• pp.57-64
• /
• 2022

A study on propllers for unmaned aerial vehicles is conducted using the open softwares. Since the shape of the propeller is closely related to the thurst characteristics of the propulsion system, adopting an appropriate propeller will significantly reflect stable aerodynamic performances. In this study, propellers for unmanned aerial vehicles were modeled by using OpenVSP and Propel for comparison, the thrust characteristics according to the number of blades and the diameter of the propeller were analyzed. In addition, the tendency of thrust characteristics according to various propeller pitch angles was confirmed. Based on the analysis results of this study, the applicability of the propeller shape to the design of the unmanned aerial vehicle was confirmed. It is shownthat the analysis results of this study can be utilized when modeling the propeller shape in research such as a conceptual design of unmanned aerial vehicle. In this case, it should be noted that OpenVSP does not involve the viscous effect of air.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.125-132
• /
• 2023

Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.633-646
• /
• 2023

The increases in UAVs(Unman Aerial Vehicle) such as drone result in safety issues and the threat of illegal drone as well. Recognizing the need for Drone forensics, domestic and foreign organizations and agencies are trying to establish drone forensic guidelines. The definition of Drone forensic artifacts and examination of forensic tools must be provided, in order to establish a practical drone forensic framework on security sites and also the concept of drone live forensic which provides meaningful data that can be extracted in a live state. In this study, the drone forensic methodology covering various types of drones is explained, and the practical forensic methodology with live forensic PoC(Proof Of Concept) tools; LiPFo(Live-PX4-Forenensic) is proposed.

• Telecommunications review
• /
• v.24 no.4
• /
• pp.468-480
• /
• 2014

The current-generation avionics systems are based on a federated architecture, where an electronic device runs a single software module or application that collaborates with other devices through a network. This architecture makes the internal system architecture very complicate, and gives rise to issues of Size, Weight, and Power (SWaP). In this paper, we show that the partitioning defined by ARINC 653 can efficiently deal with the SWaP issues on small unmanned aerial vehicles, where the SWaP issues are extremely severe. We especially install the integrated mission system on real hexacopter and quadcopter and perform successful flight tests. The presented software technology for integrated mission system and software consolidation methodology can provide a valuable reference for other SWaP sensitive real-time systems.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1255-1255
• /
• 2022

Recently, research on digital twins to generate digital information and manage construction in real-time using advanced technology is being conducted actively. However, in the construction industry, it is difficult to optimize and apply digital technology in real-time due to the nature of the construction industry in which information is constantly fluctuating. In addition, inaccurate information on the topography of construction projects is a major challenge for earthmoving processes. In order to ultimately improve the cost-effectiveness of construction projects, both construction quality and productivity should be addressed through efficient construction information management in large-scale earthworks projects. Therefore, in this study, a 3D digital map-based AR site management work support system for higher efficiency and accuracy of site management was proposed by using unmanned aerial vehicles (UAV) in wide earthworks construction sites to generate point cloud data, building a 3D digital map through acquisition and analysis of on-site sensor-based information, and performing the visualization with AR at the site By utilizing the 3D digital map-based AR site management work support system proposed in this study, information is able to be provided quickly to field managers to enable an intuitive understanding of field conditions and immediate work processing, thereby reducing field management sluggishness and limitations of traditional information exchange systems. It is expected to contribute to the improvement of productivity by overcoming factors that decrease productivity in the construction industry and the improvement of work efficiency at construction sites.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.31 no.1
• /
• pp.11-17
• /
• 2023

In this study, the correlation analysis between total system error and environmental factor variables was performed to confirm the effect on the performance of the integrated navigation system by various environmental factors. To collect flight data of hybrid vertical take-off and landing UAVs, scenarios including various turning sections and straight sections such as left turn, right turn, turning rate, and path change angle were selected, and environmental data of wind direction, wind speed, temperature, air pressure, and humidity were collected in real time through weather station. As a result of the correlation analysis between the collected flight data and environmental data, it was concluded that the performance of the integrated navigation system by environmental factors within the collected data was not significant affected and was robust.