Joonwon Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Joonwon Choi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Inseok Hwang
School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA
4 shared publications - Hyondong Oh
Korea Advanced Institute of Science and Technology (KAIST)
3 shared publications - Sooyung Byeon
School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA
3 shared publications Gangik Cho
1 shared publicationGeunsik Bae
1 shared publication- Heungsik Lim
Agency for Defense Development Aerospace Technology Research Institute Korea
1 shared publication
Latest Publications
- 24 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 33 (2) , 788-798
Data-Driven Closed-Loop Reachability Analysis for Nonlinear Human-in-the-Loop Systems Using Gaussian Mixture Model
This article presents data-driven algorithms to perform the reachability analysis of nonlinear human-in-the-loop (HITL) systems. Such systems require consideration of the human control policy, otherwise might result in a conservative reachable set. However, formulating the human control policy in a mathematically tractable form is challenging, and thus, it is commonly ignored or simplified in many applications. To tackle this problem, we propose Gaussian mixture model (GMM)-based data-driven algorithms that can explicitly consider the human control policy during the reachability analysis of an HITL system. The proposed algorithms learn the human control policy as a GMM using the given trajectory. Then, the control input from the human operator is predicted based on the trained GMM by leveraging the Gaussian mixture regression (GMR), thereby facilitating the closed-loop forward stochastic reachability analysis. In this article, we examine two types of human control policies, state-independent and state-dependent, and propose the respective algorithms. We also tested our proposed algorithms using the human subject experimental data and demonstrated to generate more accurate results compared with other existing algorithms.
- 24 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 33 (2) , 788-798
Data-Driven Closed-Loop Reachability Analysis for Nonlinear Human-in-the-Loop Systems Using Gaussian Mixture Model
This article presents data-driven algorithms to perform the reachability analysis of nonlinear human-in-the-loop (HITL) systems. Such systems require consideration of the human control policy, otherwise might result in a conservative reachable set. However, formulating the human control policy in a mathematically tractable form is challenging, and thus, it is commonly ignored or simplified in many applications. To tackle this problem, we propose Gaussian mixture model (GMM)-based data-driven algorithms that can explicitly consider the human control policy during the reachability analysis of an HITL system. The proposed algorithms learn the human control policy as a GMM using the given trajectory. Then, the control input from the human operator is predicted based on the trained GMM by leveraging the Gaussian mixture regression (GMR), thereby facilitating the closed-loop forward stochastic reachability analysis. In this article, we examine two types of human control policies, state-independent and state-dependent, and propose the respective algorithms. We also tested our proposed algorithms using the human subject experimental data and demonstrated to generate more accurate results compared with other existing algorithms.
- Open Access
- 26 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 13 (3) , 1-25
Stochastic-skill-level-based Shared Control for Human Training in Urban Air Mobility Scenario
This article proposes a novel stochastic-skill-level-based shared control framework to assist human novices to emulate human experts in complex dynamic control tasks. The proposed framework aims to infer stochastic-skill-levels (SSLs) of the human novices and provide personalized assistance based on the inferred SSLs. SSL can be assessed as a stochastic variable that denotes the probability that the novice will behave similarly to experts. We propose a data-driven method that can characterize novice demonstrations as a novice model and expert demonstrations as an expert model, respectively. Then, our SSL inference approach utilizes the novice and expert models to assess the SSL of the novices in complex dynamic control tasks. The shared control scheme is designed to dynamically adjust the level of assistance based on the inferred SSL to prevent frustration or tedium during human training due to poorly imposed assistance. The proposed framework is demonstrated by a human subject experiment in a human training scenario for a remotely piloted urban air mobility vehicle. The results show that the proposed framework can assess the SSL and tailor the assistance for an individual in real time. The proposed framework is compared to practice-only training (no assistance) and a baseline shared control approach to test the human learning rates in the designed training scenario with human subjects. A subjective survey is also examined to monitor the user experience of the proposed framework.
- 26 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 13 (3) , 1-25
Open AccessStochastic-skill-level-based Shared Control for Human Training in Urban Air Mobility Scenario
This article proposes a novel stochastic-skill-level-based shared control framework to assist human novices to emulate human experts in complex dynamic control tasks. The proposed framework aims to infer stochastic-skill-levels (SSLs) of the human novices and provide personalized assistance based on the inferred SSLs. SSL can be assessed as a stochastic variable that denotes the probability that the novice will behave similarly to experts. We propose a data-driven method that can characterize novice demonstrations as a novice model and expert demonstrations as an expert model, respectively. Then, our SSL inference approach utilizes the novice and expert models to assess the SSL of the novices in complex dynamic control tasks. The shared control scheme is designed to dynamically adjust the level of assistance based on the inferred SSL to prevent frustration or tedium during human training due to poorly imposed assistance. The proposed framework is demonstrated by a human subject experiment in a human training scenario for a remotely piloted urban air mobility vehicle. The results show that the proposed framework can assess the SSL and tailor the assistance for an individual in real time. The proposed framework is compared to practice-only training (no assistance) and a baseline shared control approach to test the human learning rates in the designed training scenario with human subjects. A subjective survey is also examined to monitor the user experience of the proposed framework.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1-6
Bootstrapped Gaussian Mixture Model-Based Data-Driven Forward Stochastic Reachability Analysis
We propose a data-driven forward stochastic reachability analysis algorithm for a system with unknown dynamics. In this paper, we assume a limited number of trajectory data is available and one cannot obtain additional data from the target system. The proposed algorithm learns the evolution of the state probability density function (pdf) as a Gaussian mixture model (GMM) from the given trajectory data and computes the pdf of the future state at a desired future time instance. We leverage the bootstrapping algorithm to account for the parameter estimation error of the GMM by computing the confidence interval of the estimated parameters. Then, the bootstrapped GMM is synthesized by selecting the optimal parameters within the confidence interval that yields the most informative model, thereby providing more reliable prediction results. The proposed algorithm is demonstrated via both numerical simulations and human subject experiments.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1-6
Bootstrapped Gaussian Mixture Model-Based Data-Driven Forward Stochastic Reachability Analysis
We propose a data-driven forward stochastic reachability analysis algorithm for a system with unknown dynamics. In this paper, we assume a limited number of trajectory data is available and one cannot obtain additional data from the target system. The proposed algorithm learns the evolution of the state probability density function (pdf) as a Gaussian mixture model (GMM) from the given trajectory data and computes the pdf of the future state at a desired future time instance. We leverage the bootstrapping algorithm to account for the parameter estimation error of the GMM by computing the confidence interval of the estimated parameters. Then, the bootstrapped GMM is synthesized by selecting the optimal parameters within the confidence interval that yields the most informative model, thereby providing more reliable prediction results. The proposed algorithm is demonstrated via both numerical simulations and human subject experiments.
- Open Access
- 6 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Control Systems
- Vol. 3, 32-44
A Computational Framework for Optimal Adaptive Function Allocation in a Human-Autonomy Teaming Scenario
This article proposes a quantitative framework for optimally allocating task functions in human-autonomy teaming (HAT). HAT involves cooperation between humans and autonomous agents to achieve common goals. As humans and autonomous agents possess different capabilities, function allocation plays a crucial role in ensuring effective HAT. However, designing the best adaptive function allocation remains a challenge, as existing methods often rely on qualitative rules and intensive human-subject studies. To address this limitation, we propose a computational function allocation approach that leverages cognitive engineering, computational work models, and optimization techniques. The proposed optimal adaptive function allocation method is composed of three main elements: 1) analyze the teamwork to identify a set of all possible function allocations within a team construction, 2) numerically simulate the teamwork in temporal semantics to explore the interaction of the team with complex environments using the identified function allocations in a trial-and-error manner, and 3) optimize the adaptive function allocation with respect to a given situation such as physical conditions, available information resources, and human mental workload. For the optimization, we utilize performance metrics such as task performance, human mental workload, and coherency in function allocations. To illustrate the effectiveness of the proposed framework, we present a simulated HAT scenario involving a human work model and drone fleet for last-mile delivery in disaster relief operations.
- 6 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Control Systems
- Vol. 3, 32-44
Open AccessA Computational Framework for Optimal Adaptive Function Allocation in a Human-Autonomy Teaming Scenario
This article proposes a quantitative framework for optimally allocating task functions in human-autonomy teaming (HAT). HAT involves cooperation between humans and autonomous agents to achieve common goals. As humans and autonomous agents possess different capabilities, function allocation plays a crucial role in ensuring effective HAT. However, designing the best adaptive function allocation remains a challenge, as existing methods often rely on qualitative rules and intensive human-subject studies. To address this limitation, we propose a computational function allocation approach that leverages cognitive engineering, computational work models, and optimization techniques. The proposed optimal adaptive function allocation method is composed of three main elements: 1) analyze the teamwork to identify a set of all possible function allocations within a team construction, 2) numerically simulate the teamwork in temporal semantics to explore the interaction of the team with complex environments using the identified function allocations in a trial-and-error manner, and 3) optimize the adaptive function allocation with respect to a given situation such as physical conditions, available information resources, and human mental workload. For the optimization, we utilize performance metrics such as task performance, human mental workload, and coherency in function allocations. To illustrate the effectiveness of the proposed framework, we present a simulated HAT scenario involving a human work model and drone fleet for last-mile delivery in disaster relief operations.
- 13 September 2022
- Published by Elsevier in Aerospace Science and Technology
- Vol. 130
Autonomous ship deck landing of a quadrotor UAV using feed-forward image-based visual servoing
- 13 September 2022
- Published by Elsevier in Aerospace Science and Technology
- Vol. 130
Autonomous ship deck landing of a quadrotor UAV using feed-forward image-based visual servoing
- 21 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (6) , 5204-5219
Adversarial Swarm Defence Using Multiple Fixed-Wing Unmanned Aerial Vehicles
This paper proposes a coverage-based adversarial swarm defence algorithm. The defender swarm composed of fixed-wing unmanned aerial vehicles (UAVs) is assumed to have explosives onboard to intercept an adversarial swarm. The proposed approach consists of two steps: i) impact point optimization and ii) model predictive control (MPC)-based impact time control. The impact point optimization periodically optimizes impact points for the corresponding UAVs to maximize the coverage within the hostile swarm while minimizing the common impact time. The optimization domain is limited to a physically reachable area of UAVs with the common impact time. Besides, the MPC-based impact time controller is designed to ensure the multiple UAVs to arrive the generated time-varying impact points simultaneously. Numerical simulations are performed to prove the feasibility and efficiency of the proposed swarm defence algorithm.
- 21 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (6) , 5204-5219
Adversarial Swarm Defence Using Multiple Fixed-Wing Unmanned Aerial Vehicles
This paper proposes a coverage-based adversarial swarm defence algorithm. The defender swarm composed of fixed-wing unmanned aerial vehicles (UAVs) is assumed to have explosives onboard to intercept an adversarial swarm. The proposed approach consists of two steps: i) impact point optimization and ii) model predictive control (MPC)-based impact time control. The impact point optimization periodically optimizes impact points for the corresponding UAVs to maximize the coverage within the hostile swarm while minimizing the common impact time. The optimization domain is limited to a physically reachable area of UAVs with the common impact time. Besides, the MPC-based impact time controller is designed to ensure the multiple UAVs to arrive the generated time-varying impact points simultaneously. Numerical simulations are performed to prove the feasibility and efficiency of the proposed swarm defence algorithm.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 287-296
Decentralized Hybrid Flocking Guidance for a Swarm of Small UAVs
Flocking is defined as flying in groups without colliding into each other through data exchange where each UAV applies a decentralized algorithm. In this paper, hybrid flocking control is proposed by using three types of guidance methods: vector field, Cucker-Smale model, and potential field. Typically, hybrid flocking control using several methods can lead to generating conflicting commands and thus degrading the performance of the mission. To address this issue, the adaptive Cucker-Smale model is proposed. Besides, we use social learning particle swarm optimization to determine the optimal weightings between guidance methods. It is verified through numerical simulations that the optimal weighting for missions such as loitering and target tracking results in effective flocking.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 287-296
Decentralized Hybrid Flocking Guidance for a Swarm of Small UAVs
Flocking is defined as flying in groups without colliding into each other through data exchange where each UAV applies a decentralized algorithm. In this paper, hybrid flocking control is proposed by using three types of guidance methods: vector field, Cucker-Smale model, and potential field. Typically, hybrid flocking control using several methods can lead to generating conflicting commands and thus degrading the performance of the mission. To address this issue, the adaptive Cucker-Smale model is proposed. Besides, we use social learning particle swarm optimization to determine the optimal weightings between guidance methods. It is verified through numerical simulations that the optimal weighting for missions such as loitering and target tracking results in effective flocking.