• ETRI Journal
• /
• 제44권6호
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• International Journal of Aeronautical and Space Sciences
• /
• 제2권1호
• /
• pp.93-102
• /
• 2001

Flight control design for the autonomous waypoint navigation of aircraft is presented in this study. The waypoints are defined in terms of desired longitude and latitude. The control design is conducted in longitudinal and lateral directions, respectively. The lateral control is based upon coordinated turn strategy for which no sideslip is allowed under the turning maneuver. The longitudinal control is mainly focused on altitude hold during navigation. Neural network control approach is applied to the altitude-hold mode control. Simulation of the proposed control strategy has been performed under various conditions. A graphical simulation tool was developed to visually demonstrate the control technique developed in this study. A method to simulate the gas turbine transient behavior is developed. The basic principles of the method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권4호
• /
• pp.293-298
• /
• 2006

In this paper, a sensor fusion based robot navigation method for the autonomous control of a miniature human interaction robot is presented. The method of navigation blends the optimality of the Fuzzy Neural Network(FNN) based control algorithm with the capabilities in expressing knowledge and learning of the networked Intelligent Robotic Space(IRS). States of robot and IR space, for examples, the distance between the mobile robot and obstacles and the velocity of mobile robot, are used as the inputs of fuzzy logic controller. The navigation strategy is based on the combination of fuzzy rules tuned for both goal-approach and obstacle-avoidance. To identify the environments, a sensor fusion technique is introduced, where the sensory data of ultrasonic sensors and a vision sensor are fused into the identification process. Preliminary experiment and results are shown to demonstrate the merit of the introduced navigation control algorithm.

• 한국정보통신학회논문지
• /
• 제25권1호
• /
• pp.75-80
• /
• 2021

측위 기술은 증강현실, 스마트 팩토리, 자율주행 등에서 중요한 기능을 수행하고 있다. 측위 기술 중에서 비콘을 이용한 측위 방법은 RSSI(Receiver Signal Strength Indicator) 값의 편차로 인하여 도전적인 과제로 여겨져 왔다. 본 논문에서는 수신기의 RSSI 값을 입력으로 하고 거리를 목표 값으로 하는 신경망을 학습시켜서 이동하는 객체에 대한 위치를 예측하였다. 이를 수행하기 위해 RSSI 대비 거리 실측값을 수집하였다. 수집한 데이터로 합성 데이터를 만들기 위한 신경망을 도입하였다. 이 신경망을 바탕으로 거리 대비 RSSI 값을 예측하였다. 합성 데이터를 바탕으로 가상으로 좌표계를 구성하여 객체의 위치를 예측하였다. 합성 데이터를 생성하기 위한 신경망으로 RSSI의 표준편차는 구하였고 이 값을 기반으로 가상환경에서 단말의 위치를 추적하는 신경망을 학습시켜 객체의 좌표를 추정하였다.

• 자동차안전학회지
• /
• 제16권1호
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권3호
• /
• pp.327-336
• /
• 2004

In distributed autonomous mobile robot system, each robot (predator or prey) must behave by itself according to its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot have both learning and evolution ability to adapt to dynamic environment. This paper proposes a pursuing system utilizing the artificial life concept where virtual robots emulate social behaviors of animals and insects and realize their group behaviors. Each robot contains sensors to perceive other robots in several directions and decides its behavior based on the information obtained by the sensors. In this paper, a neural network is used for behavior decision controller. The input of the neural network is decided by the existence of other robots and the distance to the other robots. The output determines the directions in which the robot moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behaviors fit adequately to the goal and can express group behaviors. The validity of the system is verified through simulation. Besides, in this paper, we could have observed the robots' emergent behaviors during simulation.

• 한국정보기술학회논문지
• /
• 제16권12호
• /
• pp.75-83
• /
• 2018

최근 자율 주행 자동차에 대한 연구가 활발하다. 자율 주행 자동차는 보행자 검출 및 인식 기술이 중요하다. 최근에 주로 사용되는 CNN(Convolutional Neural Network)을 이용한 보행자 검출은 대체로 좋은 성능을 보이나 영상의 환경에 따른 성능 저하가 있다. 본 논문에서는 LGP-FL(Local Gradient Pattern-Feature Layer)을 추가한 CNN Network를 기반으로 해마 신경망의 장기 기억 구조를 적용한 보행자 검출 시스템을 제안한다. 먼저 입력 이미지를 $227{\times}227$의 크기로 변경한다. 그 후 총 5개 층의 Convolution layer를 거쳐 특징을 추출한다. 그 과정에서 추가되는 LGP-FL에서는 LGP 특징 패턴을 추출하여 출현 빈도수가 높은 패턴을 장기 기억 장치에 저장한다. 이후 검출 과정에서 밝기 및 색상 변화에 강인한 LGP 특징 패턴 정보를 이용해 검출함으로써 보다 정확하게 보행자를 검출할 수 있다. 기존의 방법들과 제안하는 기법의 비교를 통해 약 1~4%의 검출률 증가를 확인하였다.

• International journal of advanced smart convergence
• /
• 제6권4호
• /
• pp.73-79
• /
• 2017

The Convolutional Neural Network (CNN) has shown an excellent performance in computer vision task. Applications of CNN include image classification, object detection in images, autonomous driving, etc. This paper will evaluate the performance of CNN model with ReLU and SELU as activation function. The evaluation will be performed on four different choices of hyperparameter which are initialization method, network configuration, optimization technique, and regularization. We did experiment on each choice of hyperparameter and show how it influences the network convergence and test accuracy. In this experiment, we also discover performance improvement when using SELU as activation function over ReLU.

• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.726-734
• /
• 2007

Generally, a mobile robot is moved by original input programs. However, it is very hard for a non-expert to change the program generating the moving path of a mobile robot, because he doesn't know almost the teaching command and operating method for driving the robot. Therefore, the teaching method with speech command for a handicapped person without hands or a non-expert without an expert knowledge to generate the path is required gradually. In this study, for easily teaching the moving path of the autonomous mobile robot, the autonomous mobile robot with the function of speech recognition is developed. The use of human voice as the teaching method provides more convenient user-interface for mobile robot. To implement the teaching function, the designed robot system is composed of three separated control modules, which are speech preprocessing module, DC servo motor control module, and main control module. In this study, we design and implement a speaker dependent isolated word recognition system for creating moving path of an autonomous mobile robot in the unknown environment. The system uses word-level Hidden Markov Models(HMM) for designated command vocabularies to control a mobile robot, and it has postprocessing by neural network according to the condition based on confidence score. As the spectral analysis method, we use a filter-bank analysis model to extract of features of the voice. The proposed word recognition system is tested using 33 Korean words for control of the mobile robot navigation, and we also evaluate the performance of navigation of a mobile robot using only voice command.

• 센서학회지
• /
• 제10권2호
• /
• pp.134-141
• /
• 2001

본 논문은 자기장을 이용한 자율주행 전기자동차의 조향 제어에 대한 연구이다. 도로의 중앙에 일정 간격으로 영구자석을 설치하고 차량에 자기 센서를 장착하여 차량의 이동에 따른 자기장의 변화를 측정하여 조향 제어가 되도록 하였다. 단일 자석에 의한 자계 분포로부터 일정한 간격으로 나열된 영구자석에 의한 자계를 분석하였고, 이를 이용하여 자석에 의한 직선 및 곡선 도로를 만들어 주행 시뮬레이션을 하였다. 차량의 조향 제어를 위해 신경회로망을 이용하여 제어기를 구성하고, 자석을 설치하여 만든 실험도의에서 실제 제작한 전기자동차를 이용하여 주행 실험을 하였다. 실제 주행 실험에서 차체와 외부 지자기에 의한 영향을 보상하여 제안된 방법에 의한 자율 주행 차량의 자율 주행이 가능함을 확인하였다.