Minsoo Kim

Minsoo Kim

Auto-generated profile, based on publicly available information

Minsoo Kim

Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
5 December 2022 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
MKMinsoo Kim
Minsoo Kim
JAJoonwoo Ahn
Joonwoo Ahn
JPJaeheung Park
Jaeheung Park
Rapidly-exploring random tree (RRT) has been studied for autonomous parking as it quickly finds an initial path and is easily scalable in complex environments. However, the planning time increases by searching for the path in narrow parking spots. To reduce the planning time, the target tree algorithm, which substitutes a parking goal in RRT with a set (target tree) of backward parking paths, was proposed. However, as it consists of circular and straight paths, it deteriorates parking accuracy because of curvature-discontinuity. Moreover, the planning time increases in complex environments; backward paths can be blocked by obstacles. Therefore, this paper introduces the TargetTree-RRT* algorithm for complex environments. First, a target tree is designed using clothoid paths to address such curvature-discontinuity. Second, to reduce the planning time further, a cost function is defined to initialize a proper target tree that considers obstacles. By integrating with optimal-variant RRT and searching for the shortest path, the proposed TargetTree-RRT* algorithm obtains a near-optimal path as the sampling time increases. Experiment results in real environments showed that the vehicle parked more accurately, and continuous-curvature paths were obtained more quickly and with higher success rates than those acquired using other sampling-based and other types of planning algorithms. Note to Practitioners —This work was motivated by the need to develop a fast and practical path planning algorithm for autonomous parking, not only in simple environments but also in complex environments. Sampling-based planning algorithms have been studied in this area, with the advantages of rapid planning of an initial path and easily reflecting vehicle’s constraints. Nevertheless, in cluttered environments, it needs considerable time to obtain a path for the autonomous vehicle easy for tracking and precise parking. To address the aforementioned issue, this article presents the TargetTree-RRT* algorithm. It finds a path by replacing a parking goal with a set of pre-defined continuous-curvature paths considering cluttered environments. TargetTree-RRT* achieves better performance for real parking scenarios and rapidly obtains a near-optimal parking path, compared to other parking path planners. The proposed algorithm is not limited to autonomous vehicles. It can be applied to other unmanned vehicles or robots, such as autonomous underwater vehicles (AUVs). In any application where the goal of path planning can be replaced with predefined standardized paths, the proposed algorithm can be extended.

14 June 2021 in IEEE Access
Verified
Journal Article
Open access
MKMinsung Kim
Minsung Kim
DLDonggil Lee
Donggil Lee
JAJoonwoo Ahn
Joonwoo Ahn
MKMinsoo Kim
Minsoo Kim
JPJaeheung Park
Jaeheung Park
This paper proposes an algorithm for path-following and collision avoidance of an autonomous vehicle based on model predictive control (MPC) using time-varying and non-uniformly spaced horizon. The MPC based on non-uniformly spaced horizon approach uses the time intervals that are small for the near future, and time intervals that are large for the distant future, to extend the length of the whole prediction horizon with a fixed number of prediction steps. This MPC has the advantage of being able to detect obstacles in advance because it can see the distant future. However, the presence of longer time interval samples may lead to poor path-following performance, especially for paths with high curvature. The proposed algorithm performs proper adjustment of the prediction interval according to a given situation. For sections with large curvature, it uses the short prediction intervals to increase the path-following performance; further, to consider obstacles over a wider range, it uses the long prediction intervals. This technique allows simultaneous improvement of the path-following performance and the range of obstacle avoidance with fixed computational complexity. The effectiveness of the proposed method is verified through an open-source simulator, CARLA and real-time experiments.

29 May 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
MKMinsoo Kim
Minsoo Kim
AEArthur Esquerre-Pourtère
Arthur Esquerre-Pourtère
JPJaeheung Park
Jaeheung Park
Real-time sampling-based planners increasingly use learned sampling distributions for faster planning in autonomous vehicles. These planners employ a neural network to predict the optimal path and bias some samples toward the path. However, inherent prediction inaccuracies of the network often lead to suboptimal paths, especially in narrow spaces. Learned samples should be used carefully based on accuracy, as inaccurate samples can degrade planning performance. To address this problem, this paper proposes Learned Adaptive Anytime TargetTree-RRT* (LA3T*) algorithm. The proposed planner introduces the adaptive biasing ratio. The approach learns to assess the reliability of the learned distribution using the network’s confidence. This confidence approximates a proper ratio of learned samples used, thereby adaptively maximizing planning performance while considering a level of prediction accuracy. Furthermore, the LA3T* algorithm incorporates the target tree algorithm. The goal pose is replaced with a set (target tree) of pre-defined optimal path segments, reducing computational efforts in narrow regions. Experiments in various driving tasks explore the benefits of each component through ablation studies. The proposed algorithm significantly increases the success rate and reduces the path length in simulated and real-world scenarios compared to other sampling-based methods.

24 January 2015
Verified
Conference Paper
Open access
HSHyunseok Seo
Hyunseok Seo
JKJinwook Kim
Jinwook Kim
MKMin-Soo Kim
Min-Soo Kim
Fast processing graph algorithms for large-scale graphs becomes increasingly important. Besides, there have been many attempts to process graph applications by exploiting the massive amount of parallelism of GPUs. However, most of the existing methods fail to process large-scale graphs that do not fit in GPU device memory. We propose a fast and scalable parallel processing method GStream that fully exploits the computational power of GPUs for processing large-scale graphs (e.g., billions vertices) very efficiently. It exploits the concept of nested-loop theta-join and multiple asynchronous GPU streams. Extensive experimental results show that GStream consistently and significantly outperforms the state-of-the art method.

31 December 2016 in International Journal of Software Engineering and Its Applications
Verified
Journal Article
Closed access
MKMin-Soo Kim
Min-Soo Kim
CLChoong Ho Lee
Choong Ho Lee

5 August 2022 in Journal of Advanced Transportation
Verified
Journal Article
Open access
PDF file
JAJoonwoo Ahn
Joonwoo Ahn
YLYangwoo Lee
Yangwoo Lee
MKMinsoo Kim
Minsoo Kim
JPJaeheung Park
Jaeheung Park
Autonomous vehicles need a driving method to be less dependent on localization data to navigate intersections in unstructured environments because these data may not be accurate in such environments. Methods of distinguishing branch roads existing at intersections using vision and applying them to intersection navigation have been studied. Model-based detection methods recognize patterns of the branch roads, but are sensitive to sensor noise and difficult to apply to various complex situations. Therefore, this study proposes a method for detecting the branch roads at the intersection using deep learning. The proposed multi-task deep neural network distinguishes the branch road into a shape of rotated bounding boxes and also recognizes the drivable area to consider obstacles inside the box. Through the output of the network, an occupancy grid map consisting of one branch road at an intersection is obtained, which can be used as an input to the existing motion-planning algorithms that do not consider intersections. Experiments in real environments show that the proposed method detected the branch roads more accurately than the model-based detection method, and the vehicle drove safely at the intersection.