arXiv subjects

Jongmin Park

Publications and source records attributed to Jongmin Park.

25 records · Page 2Linked to original sources

arXiv2022

Indoor Path Planning for Multiple Unmanned Aerial Vehicles via Curriculum Learning

Multi-agent reinforcement learning was performed in this study for indoor path planning of two unmanned aerial vehicles (UAVs). Each UAV performed the task of moving as fast as possible from a randomly paired initial position to a goal position in an environment with obstacles. To minimize training time and prevent the damage of UAVs, learning was performed by simulation. Considering the non-stationary characteristics of the multi-agent environment wherein the optimal behavior varies based on the actions of other agents, the action of the other UAV was also included in the state space of each UAV. Curriculum learning was performed in two stages to increase learning efficiency. A goal rate of 89.0% was obtained compared with other learning strategies that obtained goal rates of 73.6% and 79.9%.

cs.RO↗

arXiv2022

Anatomy of Einstein Manifolds

An Einstein manifold in four dimensions has some configuration of $SU(2)_+$ Yang-Mills instantons and $SU(2)_-$ anti-instantons associated with it. This fact is based on the fundamental theorems that the four-dimensional Lorentz group $Spin(4)$ is a direct product of two groups $SU(2)_\pm$ and the vector space of two-forms decomposes into the space of self-dual and anti-self-dual two-forms. It explains why the four-dimensional spacetime is special for the stability of Einstein manifolds. We now consider whether such a stability of four-dimensional Einstein manifolds can be lifted to a five-dimensional Einstein manifold. The higher-dimensional embedding of four-manifolds from the viewpoint of gauge theory is similar to the grand unification of Standard Model since the group $SO(4) \cong Spin(4)/\mathbb{Z}_2 = SU(2)_+ \otimes SU(2)_-/\mathbb{Z}_2$ must be embedded into the simple group $SO(5) = Sp(2)/\mathbb{Z}_2$. Our group-theoretic approach reveals the anatomy of Riemannian manifolds quite similar to the quark model of hadrons in which two independent Yang-Mills instantons represent a substructure of Einstein manifolds.

hep-th↗

arXiv2021

Indoor Path Planning for an Unmanned Aerial Vehicle via Curriculum Learning

In this study, reinforcement learning was applied to learning two-dimensional path planning including obstacle avoidance by unmanned aerial vehicle (UAV) in an indoor environment. The task assigned to the UAV was to reach the goal position in the shortest amount of time without colliding with any obstacles. Reinforcement learning was performed in a virtual environment created using Gazebo, a virtual environment simulator, to reduce the learning time and cost. Curriculum learning, which consists of two stages was performed for more efficient learning. As a result of learning with two reward models, the maximum goal rates achieved were 71.2% and 88.0%.

cs.RO↗

arXiv2020

Effect of Outlier Removal from Temporal ASF Corrections on Multichain Loran Positioning Accuracy

The widely used global navigation satellite systems (GNSSs) are vulnerable to radio frequency interference (RFI). Long-range navigation (Loran), a terrestrial navigation system, can compensate for this weakness; however, it suffers from low positioning accuracy, and studies are under way to improve its positioning performance. One such study has proposed the multichain Loran positioning method that uses the signals of transmitting stations belonging to different chains. Although the multichain Loran positioning performance is superior to the performance of conventional methods, the additional secondary factor (ASF) can still degrade its positioning accuracy. To mitigate the effects of temporal ASF, which is one of the ASF components, it is necessary to obtain temporal correction data from a nearby reference station at a known location. In this study, an experiment is performed to verify the effect of removing the outliers in the temporal correction data on the multichain Loran positioning accuracy.

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↗

arXiv2020

Neural Network-Based Ranging with LTE Channel Impulse Response for Localization in Indoor Environments

A neural network (NN)-based approach for indoor localization via cellular long-term evolution (LTE) signals is proposed. The approach estimates, from the channel impulse response (CIR), the range between an LTE eNodeB and a receiver. A software-defined radio (SDR) extracts the CIR, which is fed to a long short-term memory model (LSTM) recurrent neural network (RNN) to estimate the range. Experimental results are presented comparing the proposed approach against a baseline RNN without LSTM. The results show a receiver navigating for 100 m in an indoor environment, while receiving signals from one LTE eNodeB. The ranging root-mean squared error (RMSE) and ranging maximum error along the receiver's trajectory were reduced from 13.11 m and 55.68 m, respectively, in the baseline RNN to 9.02 m and 27.40 m, respectively, with the proposed RNN-LSTM.

eess.SP↗

arXiv2020

NTIRE 2020 Challenge on NonHomogeneous Dehazing

This paper reviews the NTIRE 2020 Challenge on NonHomogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor. NH-Haze is the first realistic nonhomogeneous haze dataset that provides ground truth images. The nonhomogeneous haze has been produced using a professional haze generator that imitates the real conditions of haze scenes. 168 participants registered in the challenge and 27 teams competed in the final testing phase. The proposed solutions gauge the state-of-the-art in image dehazing.

cs.CV↗