• Journal of the Korea Society for Simulation
• /
• v.27 no.4
• /
• pp.1-8
• /
• 2018

The most common way to control a target point using artificial intelligence is through reinforcement learning. However, it had to process complicated calculations that were difficult to implement in order to process reinforcement learning. In this paper, the enhanced Proximal Policy Optimization (PPO) algorithm was used to simulate finding the planned flight trajectory to reach the target point in the virtual environment. In this paper, we simulated how this problem was used to find the planned flight trajectory to reach the target point in the virtual environment using the enhanced Proximal Policy Optimization(PPO) algorithm. In addition, variables such as changes in trajectory, effects of rewards, and external winds are added to determine the zero conditions of external environmental factors on flight trajectory learning, and the effects on trajectory learning performance and learning speed are compared. From this result, the simulation results have shown that the agent can find the optimal trajectory in spite of changes in the various external environments, which will be applicable to the actual vehicle.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.307-310
• /
• 1996

In this paper, we deal with some numerical analyses of a re-entry vehicle in a 2-dimensional plane as an optimal control problem. To reduce the dynamic load, the heat load and the oscillation in the trajectory, we researched the trajectories in which the load factor or the rate of flight path angle was minimized during re-entry. In addition to that, taking advantage of the monotonous subarc method and the folded time-axis method, we tried to find the heat-less and load-less trajectory with combinations of some sectional functionals so that we can achieve more comfortability.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.4 no.5
• /
• pp.397-404
• /
• 1999

In this paper, several control methods for the discontinuous mode PWlvl-SRC are investigated with the l linearized small signal model. In order to analyze the stability and dyncunic characteristics of the controlled s system, the root locus as a function of the normaliz떠 output current(]\iOC) for a given normalized output v voltage(NOV) is employed. FurLhem10re, in this paper, the “Optimal trajectory control of PWM-SRC" is newly p propos(xl and its good dvnamic performances are evaluated with other four control laws.laws.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.19 no.5
• /
• pp.463-469
• /
• 2014

This paper proposes a maximum torque operation strategy for the direct torque control of a surface-mounted permanent-magnet synchronous motor (SPMSM). The proposed method analyzes the available operation region of the stator flux of the SPMSM under voltage and current constraints. Based on this analysis, the optimal stator flux trajectory that yields the maximum torque is obtained across the entire operation region, including constant torque and constant power regions. The proposed strategy is also applicable in the flux-weakening region II operation of the SPMSM, which has no speed limit. The validity of the proposed method is verified through experiments conducted on an 800 W SPMSM drive system.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.3
• /
• pp.137-146
• /
• 1997

External linkage type spine motion analysis was developed for relative trunk motion respect to the pelvis. A special programs for calculation of the relative angular motion and for graphical display were also developed. The developed device assured its accuracy and conveniency after application to 15 normal vol- unteers. Compare to the normal subjects, 18 patients treated with fixations and decompression surgery showed relatively large coupling motion. Optimal trajectory of the trunk motion derived from mathematical model in flexion and extension matched well with measurement for normal subjects.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.304-306
• /
• 2001

This paper presents the obstacle avoidance of a biped walking robot using GA-Fuzzy algorithm. In the case of our previous studies the surface has been assumed to be flat. For the case of the environment with obstacles, however, the walking robot might be unnatural. Thus, we considered the surface contained obstacles that the robot can pass through. We propose the optimal leg trajectory data-base by using genetic algorithm and optimal leg trajectory movement about obstacles that exist in front of the robot using fuzzy approach. It is shown that the robot can move more naturally on the surface that contains obstacles.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.25.3-25
• /
• 2001

This paper describes a control method of a robot cooperating with a human. A task in which a robot and a human move an object cooperatively is considered. To develop the force controller of the robot, the characteristics of human arm are investigated. The arm is forced to move along a trajectory in the experiment and the exerted force and the displacement are analyzed, It is found the force characteristics of the human arm is regarded as an optimal damper with minimizing a cost function. Then, the model is implemented to a robot and the cooperation of the robot and a human operator is examined. The effectiveness of the derived model is investigated and the experimental results show that the human moves the object supported by the robot with a minimum jerk trajectory.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.635-642
• /
• 1989

We formulated the multi-robot trajectory problem into a series of NLP problem, each of which is that of finding the optimal tip positions of the robots for the next time step. The NLP problem is composed of an objective function and three constraints, namely: a) Joint position limits, b) Joint velocity limits, and c) Collision-avoidance constraints. By solving a series of NLP problem, optimally coordinated trajectories can be determined without requiring any prior path information. This is a novel departure from the previous approach in which either all paths or at least one path is assumed to be given. Practical application of the developed method is for optimal synthesis of multiple robot trajectories in off-line. To test the validity and effectiveness of the method, numerical examples are illustrated.

• International Journal of Aeronautical and Space Sciences
• /
• v.8 no.1
• /
• pp.54-65
• /
• 2007

Parameter optimization technique is applied to planning UAVs(Unmanned Aerial Vehicles) path under artificial enemy radar threats. The ground enemy radar threats are characterized in terms of RCS(Radar Cross Section) parameter which is a measure of exposure to the radar threats. Mathematical model of the RCS parameter is constructed by a simple mathematical function in the three-dimensional space. The RCS model is directly linked to the UAVs attitude angles in generating a desired trajectory by reducing the RCS parameter. The RCS parameter is explicitly included in a performance index for optimization. The resultant UAVs trajectory satisfies geometrical boundary conditions while minimizing a weighted combination of the flight time and the measure of ground radar threat expressed in RCS.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.3
• /
• pp.51-60
• /
• 1997

A practically applicable collision free trajectory planning technique for tow robot systems is proposed. The robot trajectories considered in this work are composed of many segments, an at the intersection points between segments robots stop to assemble, weld, ordo other jobs by the attached a end-effectors. The proposed method is based on the Planning-Coordination Decomposition where planning is to find a trajectory of each robot independently according to their tasks and coordination is to find a velocity modification profile to avoid collision with each other. To fully utilize the independently planned trajectories and to ensure no geometrical path deviation after coordination, we develop a simple technique added the minimal delay time to avoid collision just before moving along path segments. We determine the least delay time by the graphical method in the Coordination space where collisions and coordinations are easily visualized. We classify all possible cases into 3 group and derive the optimal solution for each group.