Mingi Jeong

Selected Publications

1. T-FR

   SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles

   *Mingi Jeong, *Ari Chadda, Ziang Ren, Luyang Zhao, Haowen Liu, Aiwei Zhang, Yitao Jiang, Sabriel Achong, Samuel Lensgraf, Monika Roznere, and Alberto Quattrini Li
   * These authors contributed equally to this work.

   In IEEE Transaction on Field Robotics (T-FR), Under Review – invited for a Special Issue of ICRA 2024

   Abs Bib Website

   This paper introduces the first publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, collected over 4 years and consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in autonomous surface vehicles by providing a multi- modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset by training deep learning-based open-source perception algorithms that have shown success. We expect that our dataset will contribute to development of the marine autonomy pipelines and marine (field) robotics.

   @inproceedings{jeong-tfr-2024,
     author = {Jeong, *Mingi and Chadda, *Ari and Ren, Ziang and Zhao, Luyang and Liu, Haowen and Zhang, Aiwei and Jiang, Yitao and Achong, Sabriel and Lensgraf, Samuel and Roznere, Monika and Li, Alberto Quattrini},
     booktitle = {IEEE Transaction on Field Robotics (T-FR), Under Review -- invited for a Special Issue of ICRA},
     title = {SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles},
     year = {2024},
     volume = {},
     number = {},
     cofirst = {true}
   }

2. IROS

   Active Learning-augmented Intention-aware Obstacle Avoidance of Autonomous Surface Vehicles in High-traffic Waters

   Mingi Jeong, Ari Chadda, and Alberto Quattrini Li

   In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Accepted and In press 2024

   Abs Bib Video

   This paper addresses the obstacle avoidance of Autonomous Surface Vehicles (ASVs) for safe navigation in high-traffic waters while ensuring an active state estimation of obstacle’s passing intent and reducing its uncertainty. We introduce a topological modeling of passing intent of obstacles, which can be applied to varying encounter situations based on the inherent embedding of topological concepts in COLREGs. With a Long Short-Term Memory (LSTM) neural network, we classify the passing intent of obstacles. Then, for determining the ASV maneuver, we propose a multi-objective optimization framework including information gain about the passing obstacle intent and safety. We validate the proposed approach under extensive Monte Carlo simulations (2,400 runs) with a varying number of obstacles, dynamic properties, encounter situations, and different behavioral patterns of obstacles (cooperative, non-cooperative). We also present the results from a real marine accident case study as well as real-world experiments of a real ASV with environmental disturbances, showing successful collision avoidance with our strategy in real-time.

   @inproceedings{jeong-iros-2024,
     author = {Jeong, Mingi and Chadda, Ari and Li, Alberto Quattrini},
     booktitle = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Accepted and In press},
     title = {Active Learning-augmented Intention-aware Obstacle Avoidance of Autonomous Surface Vehicles in High-traffic Waters},
     year = {2024},
     volume = {},
     number = {},
     video = {https://youtu.be/0W0d4MurzzA?si=leq1USl2cAtsgqzi}
   }

3. IROS

   Motion Attribute-Based Clustering and Collision Avoidance of Multiple In-Water Obstacles by Autonomous Surface Vehicle

   Mingi Jeong, and Alberto Quattrini Li

   In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022

   Abs Bib Video

   Navigation and obstacle avoidance in aquatic environments for autonomous surface vehicles (ASVs) in high-traffic maritime scenarios is still an open challenge, as the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is not defined for multi-encounter situations. Current state-of-the-art methods resolve single-to-single encounters with sequential actions and assume that other obstacles follow COLREGs. Our work proposes a novel real-time non-myopic obstacle avoidance method, allowing an ASV that has only partial knowledge of the surroundings within the sensor radius to navigate in high-traffic maritime scenarios. Specifically, we achieve a holistic view of the feasible ASV action space able to avoid deadlock scenarios, by proposing (1) a clustering method based on motion attributes of other obstacles, (2) a geometric framework for identifying the feasible action space, and (3) a multi-objective optimization to determine the best action. Theoretical analysis and extensive realistic experiments in simulation considering real-world traffic scenarios demonstrate that our proposed real-time obstacle avoidance method is able to achieve safer trajectories than other state-of-the-art methods and that is robust to uncertainty present in the current information available to the ASV.

   @inproceedings{jeong-moa-2022,
     author = {Jeong, Mingi and Li, Alberto Quattrini},
     booktitle = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     title = {Motion Attribute-Based Clustering and Collision Avoidance of Multiple In-Water Obstacles by Autonomous Surface Vehicle},
     year = {2022},
     volume = {},
     number = {},
     pages = {6873-6880},
     doi = {10.1109/IROS47612.2022.9981226},
     video = {https://www.youtube.com/watch?v=a305lja1lfk&t}
   }

4. UKC

   Towards Full Pipeline Development of Decision-making for Autonomous Surface Vehicles in Challenging Aquatic Environments

   Mingi Jeong, Monika Roznere, Kizito Masaba, Ari Chadda, and Alberto Quattrini Li

   In UKC (US-Korea Conference), Virginia, USA 2022
   Best presentation paper award

   Bib

   @inproceedings{jeong-UKC-2022,
     author = {Jeong, Mingi and Roznere, Monika and Masaba, Kizito and Chadda, Ari and Li, Alberto Quattrini},
     booktitle = {UKC (US-Korea Conference), Virginia, USA},
     title = {Towards Full Pipeline Development of Decision-making for Autonomous Surface Vehicles in Challenging Aquatic Environments},
     year = {2022},
     volume = {},
     number = {},
   }

5. IROS

   Efficient LiDAR-based In-water Obstacle Detection and Segmentation by Autonomous Surface Vehicles in Aquatic Environments

   Mingi Jeong, and Alberto Quattrini Li

   In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021

   Abs Bib Video

   Identifying in-water obstacles is fundamental for safe navigation of Autonomous Surface Vehicles (ASVs). This paper presents a model-free method for segmenting individual in-water objects (e.g., swimmers, buoys, boats) and shorelines from LiDAR sensor data. To reduce the computational requirement, our method first converts the 3D point cloud into a 2D spherical projection image. Then, an algorithm based on the integration of a breadth-first search and a variant of a hierarchical agglomerative clustering segments the points according to different objects. Our method addresses the sparsity and instability of the point cloud in the aquatic domain – a characteristic that makes the methods developed for self-driving cars not directly applicable for in-water obstacle segmentation, as demonstrated in our experiments. Our method is compared with other state-of-the-art approaches and is validated both in simulation and in real-world ASV deployments, with different objects and encountering scenarios. The proposed method is effective in segmenting in-water obstacles not known a priori, in real-time, outperforming other state-of-the art methods.

   @inproceedings{iros-lidar-detection-2021,
     author = {Jeong, Mingi and Li, Alberto Quattrini},
     booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     title = {Efficient LiDAR-based In-water Obstacle Detection and Segmentation by Autonomous Surface Vehicles in Aquatic Environments},
     year = {2021},
     volume = {},
     number = {},
     pages = {5387-5394},
     doi = {10.1109/IROS51168.2021.9636028},
     video = {https://www.youtube.com/watch?v=V9w549rVkdI}
   }

6. ISER

   Towards a Reliable Heterogeneous Robotic Water Quality Monitoring System: An Experimental Analysis

   *Monika Roznere, *Mingi Jeong, Lily Maechling, Nicole K Ward, Jennifer A Brentrup, Bethel Steele, Denise A Bruesewitz, Holly A Ewing, Kathleen C Weathers, Kathryn L Cottingham, and Alberto Quattrini Li
   * These authors contributed equally to this work.

   In Experimental Robotics 2021

   Abs Bib Video

   This paper describes experiments that tested the effect of robotic movement on the reliability of aquatic sensor readings. It also demonstrates the utility of a heterogeneous system of robots to advance limnological monitoring and research.

   @inproceedings{iser-2021,
     address = {Cham},
     author = {Roznere, *Monika and Jeong, *Mingi and Maechling, Lily and Ward, Nicole K and Brentrup, Jennifer A and Steele, Bethel and Bruesewitz, Denise A and Ewing, Holly A and Weathers, Kathleen C and Cottingham, Kathryn L and {Quattrini Li}, Alberto},
     booktitle = {Experimental Robotics},
     editor = {Siciliano, Bruno and Laschi, Cecilia and Khatib, Oussama},
     isbn = {978-3-030-71151-1},
     pages = {139--150},
     publisher = {Springer International Publishing},
     title = {{Towards a Reliable Heterogeneous Robotic Water Quality Monitoring System: An Experimental Analysis}},
     year = {2021},
     video = {https://www.youtube.com/watch?v=roFfrKvQ4nw},
     cofirst = {true}
   }

7. IROS

   Risk Vector-based Near miss Obstacle Avoidance for Autonomous Surface Vehicles

   Mingi Jeong, and Alberto Quattrini Li

   In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020

   Abs Bib Video

   This paper presents a novel risk vector-based near miss prediction and obstacle avoidance method. The proposed method uses the sensor readings about the pose of the other obstacles to infer their motion model (velocity and heading) and, accordingly, adapt the risk assessment and take corrective actions if necessary. Relative vector calculations allow the method to perform in real-time. The algorithm has 1.68 times faster computation performance with less change of motion than other methods and it enables a robot to avoid 25 obstacles in a congested area. Fallback behaviors are also proposed in case of faulty sensors or situation changes. Simulation experiments with parameters inferred from experiments in the ocean with our custom-made robotic boat show the flexibility and adaptability of the proposed method to many obstacles present in the environment. Results highlight more efficient trajectories and comparable safety as other state-of-the-art methods, as well as robustness to failures.

   @inproceedings{iros-risk-vector-2020,
     author = {Jeong, Mingi and Li, Alberto Quattrini},
     booktitle = {2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     title = {Risk Vector-based Near miss Obstacle Avoidance for Autonomous Surface Vehicles},
     year = {2020},
     volume = {},
     number = {},
     pages = {1805-1812},
     doi = {10.1109/IROS45743.2020.9341105},
     video = {https://www.youtube.com/watch?v=lIEZ975GsdY}
   }

8. OCEANS

   Catabot: Autonomous Surface Vehicle with an Optimized Design for Environmental Monitoring

   Mingi Jeong, Monika Roznere, Samuel Lensgraf, Amy Sniffen, Devin Balkcom, and Alberto Quattrini Li

   In Global Oceans 2020: Singapore – U.S. Gulf Coast 2020
   Student poster competition: selected top 20 submissions supporing entire travel expenses including flight, lodging, registration

   Abs Bib

   This paper presents an optimized design of research-oriented ASVs and a systematic design evaluation methodology for reliable in-water sensing. The objective is to minimize the interference on sensor readings by any ASV maneuver. The design space includes motors and sensors locations. In addition, this paper analyzes modularity - i.e., the effects of new sensor’s installation. All prototype designs are thoroughly tested using hydrostatic analyses, Computational Fluid Dynamics (CFD) simulations, and real-world field testings. Quantitative metrics, including trim, pitch, velocity magnitude of flow, and turbulence, are used to compare different configurations. Our experiments show that a motor configuration at the back part of the straights hulls is the most optimal design, resulting in high-quality data collection.

   @inproceedings{oceans-catabot-2020,
     author = {Jeong, Mingi and Roznere, Monika and Lensgraf, Samuel and Sniffen, Amy and Balkcom, Devin and Li, Alberto Quattrini},
     booktitle = {Global Oceans 2020: Singapore – U.S. Gulf Coast},
     title = {Catabot: Autonomous Surface Vehicle with an Optimized Design for Environmental Monitoring},
     year = {2020},
     volume = {},
     number = {},
     pages = {1-9},
     doi = {10.1109/IEEECONF38699.2020.9389391},
     __video = {https://www.youtube.com/watch?v=lIEZ975GsdY}
   }

9. OE

   Multi-criteria route planning with risk contour map for smart navigation

   Mingi Jeong, Eun-Bang Lee, Moonjin Lee, and Jung-Yeul Jung

   Ocean Engineering 2019
   Furture ocean technologists award

   Abs Bib

   Route planning in maritime transportation is the key to safe, efficient, and smart navigation. We propose a multi-criteria route planning technique for operators to objectively determine the routes according to their intentions. In this study, the navigational traffic risk of a route is quantitatively assessed using a model of a ship. Then, a risk contour map is visualized by structuring the data as absolute danger, hazard factors, and influential factors, which is a framework for route planning. Finally, a multi-criteria route could be modeled by considering the safety, efficiency, convenience, and ability of navigation as the main criteria. The technique assesses each criterion by analyzing the cumulative risk per distance, distance, number of waypoints, and risk gradient of derived routes. In addition, the technique proposes routes by utilizing its algorithm and incorporating contour-based projection and reference points. To verify the proposed technique, we carried out numerical simulations and evaluated actual AIS data. The results show that this technique can not only suggest goal-oriented routes but also assess the used routes. Therefore, the proposed technique can improve the route planning method to be more systematic, which contributes both to smart navigation based on the user’s purposes and to future autonomous navigation.

   @article{jeong-ocean-engineering-2019,
     title = {Multi-criteria route planning with risk contour map for smart navigation},
     journal = {Ocean Engineering},
     volume = {172},
     pages = {72-85},
     year = {2019},
     issn = {0029-8018},
     doi = {https://doi.org/10.1016/j.oceaneng.2018.11.050},
     url = {https://www.sciencedirect.com/science/article/pii/S0029801818316093},
     author = {Jeong, Mingi and Lee, Eun-Bang and Lee, Moonjin and Jung, Jung-Yeul},
     keywords = {Multi-criteria, Navigational traffic risk, Risk contour, Ship route planning, Smart navigation},
   }

10. PATENT

    A Technique to Plan a Route Based on Risk Contour Mapping

    Eun-Bang Lee, Mingi Jeong, and  Moonjin Lee

    10-2185782 Korea Patent 2020