Gihwon Kwon

Dr. Gihwon Kwon


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 November 2023 in Systems
Verified
Journal Article
Open access
PDF file
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
In the context of reinforcement learning (RL), ensuring both safety and performance is crucial, especially in real-world scenarios where mistakes can lead to severe consequences. This study aims to address this challenge by integrating temporal logic constraints into RL algorithms, thereby providing a formal mechanism for safety verification. We employ a combination of theoretical and empirical methods, including the use of temporal logic for formal verification and extensive simulations to validate our approach. Our results demonstrate that the proposed method not only maintains high levels of safety but also achieves comparable performance to traditional RL algorithms. Importantly, our approach fills a critical gap in the existing literature by offering a solution that is both mathematically rigorous and empirically validated. The study concludes that the integration of temporal logic into RL offers a promising avenue for developing algorithms that are both safe and efficient. This work lays the foundation for future research aimed at generalizing this approach to various complex systems and applications.

1 March 2023 in Scientific Journal of Gdynia Maritime University
Verified
Journal Article
Open access
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
As technology advances, hardware-centric systems are rapidly moving towards software-centric ones, and their complexity is rapidly increasing. In particular, systems directly related to safety require thorough verification. Model checking exhaustively explores the state space of the abstracted system to check whether properties written in a logical formula are achieved. In this paper, the control algorithm of the controller is verified using model checking to discover risk scenarios during the STPA steps. Two case studies are conducted using the widely used model checkers NuSMV and UPPAAL. We then explain the empirical results and compare two model checkers based on their characteristics. Finally, we discuss the benefits of applying model checking in the process of STPA.

10 February 2025 in IEEE Access
Verified
Journal Article
Open access
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
Ensuring the safety of Deep Reinforcement Learning (DRL) systems remains a significant challenge, particularly in real-time applications such as autonomous driving and robotics, where incorrect decisions can lead to catastrophic failures. This study proposes a novel safety verification framework that combines state abstraction with probabilistic model checking to quantitatively analyze failure risks. The continuous state space is clustered using the KMeans++ algorithm, enabling efficient state space reduction. A Discrete-Time Markov Chain (DTMC) model is then constructed for each cluster, capturing probabilistic transitions between abstracted states. The PRISM model checker is employed to verify failure probabilities and invariance properties, providing a rigorous quantitative evaluation of system safety. Counterexample analysis identifies critical failure paths, offering actionable insights for policy improvement. Experimental results demonstrate that the optimal number of clusters balances state space reduction with accurate failure analysis, enabling scalable verification. By leveraging model checking within an abstracted state space, this approach enhances the reliability and safety of DRL systems and establishes a pathway for their deployment in safety-critical domains.

19 May 2019
Verified
Book Chapter
Closed access
PDF file
NLNgoc-Tung La
Ngoc-Tung La
GKGihwon Kwon
Gihwon Kwon

18 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SPSohee Park
Sohee Park
GKGihwon Kwon
Gihwon Kwon
Open source software (OSS) projects rely on voluntary contributions, but their long-term survivability depends on sustained community engagement and effective problem-solving. Survivability, critical for maintaining project quality and trustworthiness, is closely linked to issue activity, as unresolved issues reflect a decline in maintenance capacity and problem-solving ability. Thus, analyzing issue retention rates provides valuable insights into a project’s health. This study evaluates OSS survivability by identifying the features that influence issue activity and analyzing their relationships with survivability. Kaplan–Meier survival analysis is employed to quantify issue activity and visualize trends in unresolved issue rates, providing a measure of project maintenance dynamics. A random forest model is used to examine the relationships between project features—such as popularity metrics, community engagement, code complexity, and project age—and issue retention rates. The results show that stars significantly reduce issue retention rates, with rates dropping from 0.62 to 0.52 as stars increase to 4000, while larger codebases, higher cyclomatic complexity, and older project age are associated with unresolved issue rates, rising by up to 15%. Forks also have a nonlinear impact, initially stabilizing retention rates but increasing unresolved issues as contributions became unmanageable. By identifying these critical factors and quantifying their impacts, this research offers actionable insights for OSS project managers to enhance project survivability and address key maintenance challenges, ensuring sustainable long-term success.

25 January 2024 in IEEE Access
Verified
Journal Article
Open access
RKRyeonggu Kwon
Ryeonggu Kwon
GKGihwon Kwon
Gihwon Kwon
SPSohee Park
Sohee Park
JCJiyoung Chang
Jiyoung Chang
SJSuhee Jo
Suhee Jo
Reinforcement learning (RL) is rapidly used in safety-centric applications. However, many studies focus on generating optimal policy that achieves maximum rewards. While maximum rewards are beneficial, safety constraints and non-functional requirements must also be considered in safety-centric applications to avoid dangerous situations. For example, in the case of food delivery robots in restaurants, RL should be used not only to find optimal policy that response to all customer requests through maximum rewards but also to consider safety constraints such as collision avoidance and non-functional requirements such as battery saving. In this paper, we investigated the fulfillment of safety constraints and non-functional requirements of learning models generated through RL with quantitative model checking. We experimented with various time steps and learning rates required for RL, targeting restaurant delivery robots. The functional requirement of these robots is to process all customer order requests, and the non-functional requirements are the number of steps and battery consumption to complete the task. Safety constraints include the amount of collision and the probability of collision. Through these experiments, we made three important findings. First, learning models that obtain maximum rewards may have a low degree of achievement of non-functional requirements and safety constraints. Second, as safety constraints are met, the degree of achievement of non-functional requirements may be low. Third, even if the maximum reward is not obtained, sacrificing non-functional requirements can maximize the achievement of safety constraints. These results show that learning models generated through RL can trade off rewards to achieve safety constraints. In conclusion, our work can contribute to selecting suitable hyperparameters and optimal learning models during RL.