Boseong Jeon

Boseong Jeon

Auto-generated profile, based on publicly available information

Boseong Jeon

Samsung Research, Samsung Electronics, Seoul, South Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
4 October 2021 in IEEE Access
Verified
Journal Article
Open access
BJBoseong Felipe Jeon
Boseong Felipe Jeon
YLYunwoo Lee
Yunwoo Lee
JCJeongjun Choi
Jeongjun Choi
JPJungwon Park
Jungwon Park
HKH. Jin Kim
H. Jin Kim
In contrast to recent developments in online motion planning to follow a single target with a drone among obstacles, a multi-target case with a single chaser drone has been hardly discussed in similar settings. Following more than one target is challenged by multiple visibility issues due to the inter-target occlusion and the limited field-of-view in addition to the possible occlusion and collision with obstacles. Also, reflecting multiple targets into planning objectives or constraints increases the computation load and numerical issues in the optimization compared to the single target case. To resolve the issues, we first develop a visibility score field for multiple targets incorporating the field-of-view limit and inter-occlusion between targets. Next, we develop a fast sweeping algorithm used to compute the field for the suitability of real-time applications. Last, we build an efficient hierarchical planning pipeline to output a chasing motion for multiple targets ensuring key objectives and constraints. For reliable chasing, we also present a prediction algorithm to forecast the movement of targets considering obstacles. The online performance of the proposed algorithm is extensively validated in challenging scenarios, including a large-scale simulation, and multiple real-world experiments in indoor and outdoor scenes. The full code implementation of the proposed method is released here: https://github.com/icsl-Jeon/dual_chaser .

3 June 2022 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
BJBoseong Felipe Jeon
Boseong Felipe Jeon
CKChanghyeon Kim
Changhyeon Kim
HSHojoon Shin
Hojoon Shin
HKH. Jin Kim
H. Jin Kim

11 October 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YLYunwoo Lee
Yunwoo Lee
JPJungwon Park
Jungwon Park
BJBoseong Jeon
Boseong Jeon
SJSeungwoo Jung
Seungwoo Jung
HKH. Jin Kim
H. Jin Kim
This letter presents a versatile trajectory planning pipeline for aerial tracking. The proposed tracker is capable of handling various chasing settings such as complex unstructured environments, crowded dynamic obstacles and multiple-target following. Among the entire pipeline, we focus on developing a predictor for future target motion and a chasing trajectory planner. For rapid computation, we employ the sample-check-select strategy: modules sample a set of candidate movements, check multiple constraints, and then select the best trajectory. Also, we leverage the properties of Bernstein polynomials for quick calculations. The prediction module predicts the trajectories of the targets, which do not overlap with static and dynamic obstacles. Then the trajectory planner outputs a trajectory, ensuring various conditions such as occlusion and collision avoidance, the visibility of all targets within a camera image and dynamical limits. We fully test the proposed tracker in simulations and hardware experiments under challenging scenarios, including dual-target following, environments with dozens of dynamic obstacles and complex indoor and outdoor spaces.

5 November 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
YLYunwoo Lee
Yunwoo Lee
JPJungwon Park
Jungwon Park
SJSeungwoo Jung
Seungwoo Jung
BJBoseong Jeon
Boseong Jeon
DODahyun Oh
Dahyun Oh
HKH. Jin Kim
H. Jin Kim
Maintaining the visibility of the target is one of the major objectives of aerial tracking missions. This paper proposes a target-visible trajectory planning pipeline using quadratic programming (QP). Our approach can handle various tracking settings, including 1) single- and dual-target following and 2) both static and dynamic environments, unlike other works that focus on a single specific setup. In contrast to other studies that fully trust the predicted trajectory of the target and consider only the visibility of the target’s center, our pipeline considers error in target path prediction and the entire body of the target to maintain the target visibility robustly. First, a prediction module uses a sample-check strategy to quickly calculate the reachable areas of moving objects, which represent the areas their bodies can reach, considering obstacles. Subsequently, the planning module formulates a single QP problem, considering path homotopy, to generate a tracking trajectory that maximizes the visibility of the target’s reachable area among obstacles. The performance of the planner is validated in multiple scenarios, through high-fidelity simulations and real-world experiments.

28 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
BJBoseong Jeon
Boseong Jeon
YCYunho Choi
Yunho Choi
TKTaehan Kim
Taehan Kim
The growing demand for real-time robotic deployment necessitates fast and on-device inference for vision-language-action (VLA) models. Within the VLA literature, efficiency has been extensively studied at the token level, such as visual token pruning. In contrast, systematic transformer layer reduction has received limited attention and, to the best of our knowledge, has not been explored for flow-based VLA models under knowledge distillation. In this work, we propose Shallow-pi, a principled knowledge distillation framework that aggressively reduces the transformer depth of both the VLM backbone and the flow-based action head, compressing the model from 18 to 6 layers. Shallow-pi achieves over two times faster inference with less than one percent absolute drop in success rate on standard manipulation benchmarks, establishing state-of-the-art performance among reduced VLA models. Crucially, we validate our approach through industrial-scale real-world experiments on Jetson Orin and Jetson Thor across multiple robot platforms, including humanoid systems, in complex and dynamic manipulation scenarios.