• ETRI Journal
• /
• v.44 no.6
• /
• 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.

• Journal of the Korean Society of Safety
• /
• v.38 no.3
• /
• pp.1-9
• /
• 2023

Most existing industrial robots have fences installed around them to ensure safety. However, industrial sites are recently being transformed into workspaces shared by both robots and humans working cooperatively, wherein the robots are without security fencing owing to the development of sensor technology. However, in the last five years (2017-2021), 16 deaths have occurred due to robots at industrial sites, with the main cause of the accidents being workers approaching an industrial robot in operation and getting entangled with or colliding into the robot and its peripherals. To prevent such accidents, multilateral research is needed. To this end, this study analyzes the nonconforming contents of safety inspections for industrial robots and demonstrates the safety performance of the safety function control system implemented in an industrial robot cell. In addition, to ensure the fundamental safety of industrial robots, this study proposes the introduction of a safety certification system so that safety functions can be implemented in the design, manufacturing, and installation stages of the robots.

• The Plant Pathology Journal
• /
• v.39 no.5
• /
• pp.449-465
• /
• 2023

Plants are challenged by various pathogens throughout their lives, such as bacteria, viruses, fungi, and insects; consequently, they have evolved several defense mechanisms. In addition, plants have developed localized and systematic immune responses due to biotic and abiotic stress exposure. Animals are known to activate DNA damage responses (DDRs) and DNA damage sensor immune signals in response to stress, and the process is well studied in animal systems. However, the links between stress perception and immune response through DDRs remain largely unknown in plants. To determine whether DDRs induce plant resistance to pathogens, Arabidopsis plants were treated with bleomycin, a DNA damage-inducing agent, and the replication levels of viral pathogens and growth of bacterial pathogens were determined. We observed that DDR-mediated resistance was specifically activated against viral pathogens, including turnip crinkle virus (TCV). DDR increased the expression level of pathogenesis-related (PR) genes and the total salicylic acid (SA) content and promoted mitogen-activated protein kinase signaling cascades, including the WRKY signaling pathway in Arabidopsis. Transcriptome analysis further revealed that defense-and SA-related genes were upregulated by DDR. The atm-2atr-2 double mutants were susceptible to TCV, indicating that the main DDR signaling pathway sensors play an important role in plant immune responses. In conclusion, DDRs activated basal immune responses to viral pathogens.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.2
• /
• pp.129-138
• /
• 2023

Acquiring precise coordinates of ground targets can be regarded as the key mission of the tactical-level military UAS(Unmanned Aerial System) operations. The coordinates deviations for the ground targets estimated from UAV (Unmanned Aerial Vehicle) images may depend on the sensor specifications and slant ranges between UAV and ground targets. It has an order of several tens to hundreds of meters for typical tactical UAV mission scenarios. In this paper, we propose a scheme that precisely acquires target coordinates from UAS by mapping image pixels to geographical coordinates based on GCP(Ground Control Points). This scheme was implemented and tested from ground control station for UAS. We took images of targets of which exact location is known and acquired the target coordinates using our proposed scheme. The experimental results showed that errors of the acquired coordinates remained within an order of several meters and the coordinates accuracy was significantly improved.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.124-130
• /
• 2023

Implementing flexible production systems in domestic and foreign automotive design parts assembly has increased demand for automation and power reduction. Consequently, transition to a hybrid production method is observed where multiple vehicles are assembled in a single assembly line. Multiple robots, 3D vision sensors, mounting positions, and correction software have complex configurations in the automotive glass mounting system. Hence, automation is required owing to significant difficulty in the assembly process of automobile parts. This study presents a primer lighting and inspection algorithm that is robust to the assembly environment of real automotive design parts using high power 'ㄷ'-shaped LED inclined lighting. Furthermore, a 2D camera was developed in the primer coating inspection system-the core technology of the glass mounting system. A primer application demo line applicable to the actual automobile production line was established using the proposed high power lighting and algorithm. Furthermore, application inspection performance was verified using this demo system. Experimental results verified that the performance of the proposed system exceeded the level required to satisfy the automobile requirements.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.296-305
• /
• 2023

The purpose of this study is to measure and compare the balance of motion between the left and right using a wearable sensor during upper limb exercise using an exercise equipment. Eight participants were asked to perform upper limb exercise using exercise equipment, and exercise data were measured through IMU sensors attached to both wrists. As a result of the PCA test, Euler Yaw(Left: 0.65, Right: 0.75), Roll(Left: 0.72, Right: 0.58), and Gyro X(Left: 0.64, Right: 0.63) were identified as the main components in the Butterfly exercise, and Euler Pitch(Left: 0.70, Right 0.70) and Gyro Z(Left: 0.70, Right: 0.71) were identified as the main components in the Lat pull down exercise. As a result of the Paired-T test of the Euler value, Yaw's Peak to Peak at Butterfly exercise and Roll's Mean, Yaw's Mean and Period at Lat pull down exercise were smaller than the significance level of 0.05, proving meaningful difference was found. In the Symmetry Index and Symmetry Ratio analysis, 89% of the subjects showed a tendency of dominant limb maintaining relatively higher angular movement performance then non-dominant limb as the Butterfly exercise proceeds. 62.5% of the subjects showed the same tendency during the Lat pull down exercise. These experimental results indicate that meaningful difference at balance of motion was found according to an increase in number of exercise trials.

• Nuclear Engineering and Technology
• /
• v.54 no.11
• /
• pp.3985-3995
• /
• 2022

The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types of radiation like Total Ionizing Dose (TID) can cause permanent damages on such nanoscale electronic devices, and current state-of-the-art technologies to tackle TID make use of expensive radiation-hardened devices. This paper focuses on a novel and different approach: using machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle TID effects and monitor them to replace before they stop working. This condition has a research challenge to anticipate when the board results in a total failure due to TID effects. We observed internal measurements of FPGA boards under gamma radiation and used three different anomaly detection machine learning (ML) algorithms to detect anomalies in the sensor measurements in a gamma-radiated environment. The statistical results show a highly significant relationship between the gamma radiation exposure levels and the board measurements. Moreover, our anomaly detection results have shown that a One-Class SVM with Radial Basis Function Kernel has an average recall score of 0.95. Also, all anomalies can be detected before the boards are entirely inoperative, i.e. voltages drop to zero and confirmed with a sanity check.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.432-440
• /
• 2023

This study introduces an efficient readout circuit designed for two-electrode electrocardiogram (ECG) recording, characterized by its low-noise and low-power consumption attributes. Unlike its three-electrode counterpart, the two-electrode ECG is susceptible to common-mode interference (CMI), causing signal distortion. To counter this, the proposed circuit integrates a common-mode charge pump (CMCP) with a window comparator, allowing for a CMI tolerance of up to 20 V_PP. The CMCP design prevents the activation of electrostatic discharge (ESD) diodes and becomes operational only when CMI surpasses the predetermined range set by the window comparator. This ensures power efficiency and minimizes intermodulation distortion (IMD) arising from switching noise. To maintain ECG signal accuracy, the circuit employs a chopper-stabilized instrumentation amplifier (IA) for low-noise attributes, and to achieve high input impedance, it incorporates a floating high-pass filter (HPF) and a current-feedback instrumentation amplifier (CFIA). This comprehensive design integrates various components, including a QRS peak detector and serial peripheral interface (SPI), into a single 0.18-㎛ CMOS chip occupying 0.54 mm². Experimental evaluations showed a 0.59 µV_RMS noise level within a 1-100 Hz bandwidth and a power draw of 23.83 µW at 1.8 V.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.6
• /
• pp.482-490
• /
• 2023

With the advent of the Fourth Industrial Revolution, many companies are developing Smart Ships to enable autonomous navigation, unmanned operation, and cost-effective shipping. In order to facilitate the operation of these Smart Ships, significant emphasis is being placed on improving external communication capabilities and developing autonomous navigation systems. Moreover, unmanned ship operation necessitates replacing of all visually observed conditions with sensors, leading to an inevitable increase in the number of sensors and actuators compared to traditional methods. However, in South Korea, the communication network for sensors and actuators primarily relies on the conventional 1:1 hardwired wiring, with the use of higher-level communication networks when necessary. Therefore, in this paper, we introduce the AS-Interface protocol, which is used for monitoring and controlling sensors and actuators, with the expectation that it will greatly contribute to the development of future Smart Ships by reducing production time, costs, and maintenance duration.

• ETRI Journal
• /
• v.45 no.6
• /
• pp.1022-1034
• /
• 2023

In this study, the impact of varying lighting conditions on recognition and decision-making was considered. The luminosity approach was presented to increase gesture recognition performance under varied lighting. An efficient framework was proposed for sensor-based sign language gesture identification, including picture acquisition, preparing data, obtaining features, and recognition. The depth images were collected using multiple Microsoft Kinect devices, and data were acquired by varying resolutions to demonstrate the idea. A case study was designed to attain acceptable accuracy in gesture recognition under variant lighting. Using American Sign Language (ASL), the dataset was created and analyzed under various lighting conditions. In ASL-based images, significant feature points were selected using the scale-invariant feature transformation (SIFT). Finally, an artificial neural network (ANN) classified hand gestures using specified characteristics for validation. The suggested method was successful across a variety of illumination conditions and different image sizes. The total effectiveness of NN architecture was shown by the 97.6% recognition accuracy rate of 26 alphabets dataset with just a 2.4% error rate.