• 제목/요약/키워드: learning trajectory

검색결과 252건 처리시간 0.023초

Pedestrian GPS Trajectory Prediction Deep Learning Model and Method

  • Yoon, Seung-Won;Lee, Won-Hee;Lee, Kyu-Chul
    • Journal of the Korea Society of Computer and Information
    • /
    • 제27권8호
    • /
    • pp.61-68
    • /
    • 2022
  • In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

Flight Trajectory Simulation via Reinforcement Learning in Virtual Environment (가상 환경에서의 강화학습을 이용한 비행궤적 시뮬레이션)

  • Lee, Jae-Hoon;Kim, Tae-Rim;Song, Jong-Gyu;Im, Hyun-Jae
    • Journal of the Korea Society for Simulation
    • /
    • 제27권4호
    • /
    • 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.

Effects of CNN Backbone on Trajectory Prediction Models for Autonomous Vehicle

  • Seoyoung Lee;Hyogyeong Park;Yeonhwi You;Sungjung Yong;Il-Young Moon
    • Journal of information and communication convergence engineering
    • /
    • 제21권4호
    • /
    • pp.346-350
    • /
    • 2023
  • Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

Implementation of a Direct Learning Control Law for the Trajectory Tracking Control of a Robot (로봇의 궤적추종제어를 위한 직접학습 제어법칙의 구현)

  • Kim, Jin-Hyoung;Ahn, Hyun-Sik;Kim, Do-Hyun
    • Proceedings of the KIEE Conference
    • /
    • 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
    • /
    • pp.694-696
    • /
    • 2000
  • In this paper, the Direct Learning Control is applied to robot's trajectory tracking control to solve the problem that lies in the existing Iterative Learning Control(ILC) and the tracking Performance is analyzed and the better approach is searched using computer simulation and experiments. It is assumed that the Direct Learning Control(DLC) is saved onto memory basically after obtaining control input Profiles for several Periodic output trajectories using the ILC. In case the new output trajectory has special relations with the previous output trajectories, there is an advantage that the desired control input profile can be obtained without iterative executions only using the DLC. The robot's tracking control system is comprised of DSP chip. A/D converter, D/A converter and high-speed pulse counter included in the control board and the performance is examined by carrying out the tracking control for the given output trajectory.

  • PDF

Model-based Reference Trajectory Generation for Tip-based Learning Controller

  • Rhim Sungsoo;Lee Soon-Geul;Lim Tae Gyoon
    • Journal of Mechanical Science and Technology
    • /
    • 제19권spc1호
    • /
    • pp.357-363
    • /
    • 2005
  • The non-minimum phase characteristic of a flexible manipulator makes tracking control of its tip difficult. The level of the tip tracking performance of a flexible manipulator is significantly affected by the characteristics of the tip reference trajectory as well as the characteristics of the flexible manipulator system. This paper addresses the question of how to best specify a reference trajectory for the tip of a flexible manipulator to follow in order to achieve the objectives of reducing : tip tracking error, residual tip vibration, and the required actuation effort at the manipulator joint. A novel method of tip-based learning controller for the flexible manipulator system is proposed in the paper, where a model of the flexible manipulator system with a command shaping filter is used to generate a smooth and realizable tip reference trajectory for a tip-based learning controller.

Application of Iterative Learning Control to 2-Mass Resonant System with Initial Position Error (위치 오차를 갖는 2관성 공진계에 대한 반복학습 제어의 적용에 관한 연구)

  • Lee, Hak-Seong
    • Proceedings of the KIEE Conference
    • /
    • 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
    • /
    • pp.307-310
    • /
    • 2003
  • In this paper, an iterative learning control method is applied to suppress the vibration of a 2-mass system which has a flexible coupling between a load an a motor. More specifically, conditions for the load speed without vibration are derived based on the steady-state condition. And the desired motor position trajectory is synthesized based on the relation between the load and motor speed. Finally, a PD-type learning iterative control law is applied for the desired motor position trajectory. Since the learning law applied for the desired trajectory guarantees the perfect tracking performance, the resulting load speed shows no vibration. In order to handle the initial position error, the PD-type learning law is changed to PID-type and a weight function is added to suppress the residual vibration caused by the initial error. The simulation results show the effectiveness of the proposed learning method.

  • PDF

Development of Augmentation Method of Ballistic Missile Trajectory using Variational Autoencoder (변이형 오토인코더를 이용한 탄도미사일 궤적 증강기법 개발)

  • Dong Kyu Lee;Dong Wg Hong
    • Journal of the Korean Society of Systems Engineering
    • /
    • 제19권2호
    • /
    • pp.145-156
    • /
    • 2023
  • Trajectory of ballistic missile is defined by inherent flight dynamics, which decided range and maneuvering characteristics. It is crucial to predict range and maneuvering characteristics of ballistic missile in KAMD (Korea Air and Missile Defense) to minimize damage due to ballistic missile attacks, Nowadays, needs for applying AI(Artificial Intelligence) technologies are increasing due to rapid developments of DNN(Deep Neural Networks) technologies. To apply these DNN technologies amount of data are required for superviesed learning, but trajectory data of ballistic missiles is limited because of security issues. Trajectory data could be considered as multivariate time series including many variables. And augmentation in time series data is a developing area of research. In this paper, we tried to augment trajectory data of ballistic missiles using recently developed methods. We used TimeVAE(Time Variational AutoEncoder) method and TimeGAN(Time Generative Adversarial Networks) to synthesize missile trajectory data. We also compare the results of two methods and analyse for future works.

Imitation Learning of Bimanual Manipulation Skills Considering Both Position and Force Trajectory (힘과 위치를 동시에 고려한 양팔 물체 조작 솜씨의 모방학습)

  • Kwon, Woo Young;Ha, Daegeun;Suh, Il Hong
    • The Journal of Korea Robotics Society
    • /
    • 제8권1호
    • /
    • pp.20-28
    • /
    • 2013
  • Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.

Robot learning control with fast convergence (빠른 수렴성을 갖는 로보트 학습제어)

  • 양원영;홍호선
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
    • /
    • pp.67-71
    • /
    • 1988
  • We present an algorithm that uses trajectory following errors to improve a feedforward command to a robot in the iterative manner. It has been shown that when the manipulator handles an unknown object, the P-type learning algorithm can make the trajectory converge to a desired path and also that the proposed learning control algorithm performs better than the other type learning control algorithm. A numerical simulation of a three degree of freedom manipulator such as PUMA-560 ROBOT has been performed to illustrate the effectiveness of the proposed learning algorithm.

  • PDF

An Application of Deep Clustering for Abnormal Vessel Trajectory Detection (딥 클러스터링을 이용한 비정상 선박 궤적 식별)

  • Park, Heon-Jei;Lee, Jun Woo;Kyung, Ji Hoon;Kim, Kyeongtaek
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • 제44권4호
    • /
    • pp.169-176
    • /
    • 2021
  • Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.