arXiv subjects

Sanghyun Kim

Publications and source records attributed to Sanghyun Kim.

45 records · Page 3Linked to original sources

arXiv2023

Object-Aware Impedance Control for Human-Robot Collaborative Task with Online Object Parameter Estimation

Physical human-robot interactions (pHRIs) can improve robot autonomy and reduce physical demands on humans. In this paper, we consider a collaborative task with a considerably long object and no prior knowledge of the object's parameters. An integrated control framework with an online object parameter estimator and a Cartesian object-aware impedance controller is proposed to realize complicated scenarios. During the transportation task, the object parameters are estimated online while a robot and human lift an object. The perturbation motion is incorporated into the null space of the desired trajectory to enhance the estimator accuracy. An object-aware impedance controller is designed using the real-time estimation results to effectively transmit the intended human motion to the robot through the object. Experimental demonstrations of collaborative tasks, including object transportation and assembly tasks, are implemented to show the effectiveness of our proposed method.

cs.RO↗

arXiv2023

Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models

Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content. The biases and harmfulness arise throughout the entire training process and are hard to completely remove, which have become significant hurdles to the safe deployment of these models. In this paper, we propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. We self-distill the diffusion model to guide the noise estimate conditioned on the target removal concept to match the unconditional one. Compared to the previous methods, our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality. Furthermore, our method allows the removal of multiple concepts at once, whereas previous works are limited to removing a single concept at a time.

cs.CV↗

arXiv2023

Machine-Learning-Based Classification of GPS Signal Reception Conditions Using a Dual-Polarized Antenna in Urban Areas

In urban areas, dense buildings frequently block and reflect global positioning system (GPS) signals, resulting in the reception of a few visible satellites with many multipath signals. This is a significant problem that results in unreliable positioning in urban areas. If a signal reception condition from a certain satellite can be detected, the positioning performance can be improved by excluding or de-weighting the multipath contaminated satellite signal. Thus, we developed a machine-learning-based method of classifying GPS signal reception conditions using a dual-polarized antenna. We employed a decision tree algorithm for classification using three features, one of which can be obtained only from a dual-polarized antenna. A machine-learning model was trained using GPS signals collected from various locations. When the features extracted from the GPS raw signal are input, the generated machine-learning model outputs one of the three signal reception conditions: non-line-of-sight (NLOS) only, line-of-sight (LOS) only, or LOS+NLOS. Multiple testing datasets were used to analyze the classification accuracy, which was then compared with an existing method using dual single-polarized antennas. Consequently, when the testing dataset was collected at different locations from the training dataset, a classification accuracy of 64.47% was obtained, which was slightly higher than the accuracy of the existing method using dual single-polarized antennas. Therefore, the dual-polarized antenna solution is more beneficial than the dual single-polarized antenna solution because it has a more compact form factor and its performance is similar to that of the other solution.

cs.LG↗

arXiv2023

Relational Context Learning for Human-Object Interaction Detection

Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers, however, may suffer from insufficient context exchange between the branches and lead to a lack of context information for relational reasoning, which is critical in discovering HOI instances. In this work, we propose the multiplex relation network (MUREN) that performs rich context exchange between three decoder branches using unary, pairwise, and ternary relations of human, object, and interaction tokens. The proposed method learns comprehensive relational contexts for discovering HOI instances, achieving state-of-the-art performance on two standard benchmarks for HOI detection, HICO-DET and V-COCO.

cs.CV↗

arXiv2023

Devil's on the Edges: Selective Quad Attention for Scene Graph Generation

Scene graph generation aims to construct a semantic graph structure from an image such that its nodes and edges respectively represent objects and their relationships. One of the major challenges for the task lies in the presence of distracting objects and relationships in images; contextual reasoning is strongly distracted by irrelevant objects or backgrounds and, more importantly, a vast number of irrelevant candidate relations. To tackle the issue, we propose the Selective Quad Attention Network (SQUAT) that learns to select relevant object pairs and disambiguate them via diverse contextual interactions. SQUAT consists of two main components: edge selection and quad attention. The edge selection module selects relevant object pairs, i.e., edges in the scene graph, which helps contextual reasoning, and the quad attention module then updates the edge features using both edge-to-node and edge-to-edge cross-attentions to capture contextual information between objects and object pairs. Experiments demonstrate the strong performance and robustness of SQUAT, achieving the state of the art on the Visual Genome and Open Images v6 benchmarks.

cs.CV↗

arXiv2022

Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas

In urban areas, global navigation satellite system (GNSS) signals are often reflected or blocked by buildings, thus resulting in large positioning errors. In this study, we proposed a machine learning approach for global positioning system (GPS) multipath detection that uses dual antennas. A machine learning model that could classify GPS signal reception conditions was trained with several GPS measurements selected as suggested features. We applied five features for machine learning, including a feature obtained from the dual antennas, and evaluated the classification performance of the model, after applying four machine learning algorithms: gradient boosting decision tree (GBDT), random forest, decision tree, and K-nearest neighbor (KNN). It was found that a classification accuracy of 82%-96% was achieved when the test data set was collected at the same locations as those of the training data set. However, when the test data set was collected at locations different from those of the training data, a classification accuracy of 44%-77% was obtained.

cs.NI↗

arXiv2021

GPS Multipath Detection Based on Carrier-to-Noise-Density Ratio Measurements from a Dual-Polarized Antenna

In this study, the global positioning system (GPS) multipath detection was performed based on the carrier-to-noise-density ratio, C/N0, measured through a dual-polarized antenna. As the right hand circular polarization (RHCP) antenna is sensitive to the signals directly received from the GPS, and the left hand circular polarization (LHCP) antenna is sensitive to the singly reflected signals, the C/N0 difference between the RHCP and LHCP measurements is used for multipath detection. Once we collected the GPS signals in a low multipath location, we calculated the C/N0 difference to obtain a threshold value that can be used to detect the multipath GPS signal received from another location. The results were validated through a ray-tracing simulation.

eess.SP↗

arXiv2021

Enhanced Accuracy Simulator for a Future Korean Nationwide eLoran System

The Global Positioning System (GPS) has become the most widely used positioning, navigation, and timing system. However, the vulnerability of GPS to radio frequency interference has attracted significant attention. After experiencing several incidents of intentional high-power GPS jamming trials by North Korea, South Korea decided to deploy the enhanced long-range navigation (eLoran) system, which is a high-power terrestrial radio-navigation system that can complement GPS. As the first phase of the South Korean eLoran program, an eLoran testbed system was recently developed and declared operational on June 1, 2021. Once its operational performance is determined to be satisfactory, South Korea plans to move to the second phase of the program, which is a nationwide eLoran system. For the optimal deployment of additional eLoran transmitters in a nationwide system, it is necessary to properly simulate the expected positioning accuracy of the said future system. In this study, we propose enhanced eLoran accuracy simulation methods based on a land cover map and transmitter jitter estimation. Using actual measurements over the country, the simulation accuracy of the proposed methods was confirmed to be approximately 10%-91% better than that of the existing Loran (i.e., Loran-C and eLoran) positioning accuracy simulators depending on the test locations.

eess.SP↗

arXiv2020

Motion Planning by Reinforcement Learning for an Unmanned Aerial Vehicle in Virtual Open Space with Static Obstacles

In this study, we applied reinforcement learning based on the proximal policy optimization algorithm to perform motion planning for an unmanned aerial vehicle (UAV) in an open space with static obstacles. The application of reinforcement learning through a real UAV has several limitations such as time and cost; thus, we used the Gazebo simulator to train a virtual quadrotor UAV in a virtual environment. As the reinforcement learning progressed, the mean reward and goal rate of the model were increased. Furthermore, the test of the trained model shows that the UAV reaches the goal with an 81% goal rate using the simple reward function suggested in this work.

cs.RO↗