Seungwon Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seungwon Choi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Tae-Wan Kim
Seoul National University
4 shared publications - Jaehyun Kim
Department of Naval Architecture and Ocean Engineering, Seoul National University (SNU), Seoul, Korea
2 shared publications - Hee-Won Chae
Korea University
1 shared publication - Jiseong Chung
Department of Naval Architecture and Ocean Engineering, Seoul National University (SNU), Seoul, Korea
1 shared publication - Kyusung Cho
SLAM Team, MAXST, Seoul, Republic of Korea
1 shared publication - Seokjoon Kim
SLAM Team, MAXST, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Sequential Testing for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments
We propose a descriptor-agnostic, multi-frame loop closure verification method that formulates LiDAR loop closure as a truncated Sequential Probability Ratio Test (SPRT). Instead of deciding from a single descriptor comparison or using fixed thresholds with late-stage Iterative Closest Point (ICP) vetting, the verifier accumulates a short temporal stream of descriptor similarities between a query and each candidate. It then issues an accept/reject decision adaptively once sufficient multi-frame evidence has been observed, according to user-specified Type-I/II error design targets. This precision-first policy is designed to suppress false positives in structurally repetitive indoor environments. We evaluate the verifier on a five-sequence library dataset, using a fixed retrieval front-end with several representative LiDAR global descriptors. Performance is assessed via segment-level K-hit precision-recall and absolute trajectory error (ATE) and relative pose error (RPE) after pose graph optimization. Across descriptors, the sequential verifier consistently improves precision and reduces the impact of aliased loops compared with single-frame and heuristic multi-frame baselines. Our implementation and dataset will be released at: https://github.com/wanderingcar/snu_library_dataset.
Open AccessSequential Testing for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments
We propose a descriptor-agnostic, multi-frame loop closure verification method that formulates LiDAR loop closure as a truncated Sequential Probability Ratio Test (SPRT). Instead of deciding from a single descriptor comparison or using fixed thresholds with late-stage Iterative Closest Point (ICP) vetting, the verifier accumulates a short temporal stream of descriptor similarities between a query and each candidate. It then issues an accept/reject decision adaptively once sufficient multi-frame evidence has been observed, according to user-specified Type-I/II error design targets. This precision-first policy is designed to suppress false positives in structurally repetitive indoor environments. We evaluate the verifier on a five-sequence library dataset, using a fixed retrieval front-end with several representative LiDAR global descriptors. Performance is assessed via segment-level K-hit precision-recall and absolute trajectory error (ATE) and relative pose error (RPE) after pose graph optimization. Across descriptors, the sequential verifier consistently improves precision and reduces the impact of aliased loops compared with single-frame and heuristic multi-frame baselines. Our implementation and dataset will be released at: https://github.com/wanderingcar/snu_library_dataset.
- 5 February 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (2) , 405-417
Improving Pose Graph Optimization via Efficient Graduated Non-convexity Scheduling
- 5 February 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (2) , 405-417
Improving Pose Graph Optimization via Efficient Graduated Non-convexity Scheduling
- Open Access
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (3) , 2998-3005
Probabilistic Kernel Optimization for Robust State Estimation
Robust state estimation is a fundamental research topic in robotics. Existing approaches like robust kernels combined with iteratively re-weighted least squares (IRLS) often require heuristic parameter selection and extensive fine-tuning. In this manuscript, we propose a novel method that optimizes kernels while preserving the advantages of existing techniques. By introducing a probabilistic interpretation of weights and residuals, our approach enables automatic parameter selection. Applied to iterative closest point (ICP) and bundle adjustment (BA), experimental results demonstrate improved convergence and robustness compared to traditional methods, eliminating the need for time-consuming parameter tuning and offering a practical solution for robust state estimation.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (3) , 2998-3005
Open AccessProbabilistic Kernel Optimization for Robust State Estimation
Robust state estimation is a fundamental research topic in robotics. Existing approaches like robust kernels combined with iteratively re-weighted least squares (IRLS) often require heuristic parameter selection and extensive fine-tuning. In this manuscript, we propose a novel method that optimizes kernels while preserving the advantages of existing techniques. By introducing a probabilistic interpretation of weights and residuals, our approach enables automatic parameter selection. Applied to iterative closest point (ICP) and bundle adjustment (BA), experimental results demonstrate improved convergence and robustness compared to traditional methods, eliminating the need for time-consuming parameter tuning and offering a practical solution for robust state estimation.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 640-647
Fast and Versatile Feature-Based LiDAR Odometry via Efficient Local Quadratic Surface Approximation
We present a fast and versatile feature-based LiDAR odometry method using local quadratic surface approximation and point-to-surface alignment. Unlike most feature-based methods, our approach approximates the local geometry of the LiDAR scan as a quadratic surface to mitigate performance degradation caused by the inconsistency between the feature class and the map's local geometry. For computational efficiency, we leverage a symmetric objective function to align features on the local surface of the map without requiring time-consuming surface parameter evaluation. Evaluation on the KITTI and Newer College dataset demonstrates that the proposed method performs better than other feature-based methods. In particular, our approach exhibits robust performance in environments where the ambiguity of feature classifications is considerable. In addition, to demonstrate the robustness of the proposed method when LiDAR scans are relatively sparse, we evaluated the proposed method on datasets collected using LiDAR with a relatively small number of scan channels.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 640-647
Fast and Versatile Feature-Based LiDAR Odometry via Efficient Local Quadratic Surface Approximation
We present a fast and versatile feature-based LiDAR odometry method using local quadratic surface approximation and point-to-surface alignment. Unlike most feature-based methods, our approach approximates the local geometry of the LiDAR scan as a quadratic surface to mitigate performance degradation caused by the inconsistency between the feature class and the map's local geometry. For computational efficiency, we leverage a symmetric objective function to align features on the local surface of the map without requiring time-consuming surface parameter evaluation. Evaluation on the KITTI and Newer College dataset demonstrates that the proposed method performs better than other feature-based methods. In particular, our approach exhibits robust performance in environments where the ambiguity of feature classifications is considerable. In addition, to demonstrate the robustness of the proposed method when LiDAR scans are relatively sparse, we evaluated the proposed method on datasets collected using LiDAR with a relatively small number of scan channels.