물체 파지점 검출 향상을 위한 분할 기반 깊이 지도 조정Segmentation-Based Depth Map Adjustment for Improved Grasping Pose Detection
- Other Titles
- Segmentation-Based Depth Map Adjustment for Improved Grasping Pose Detection
- Authors
- 신현수; 무하마드 라힐 아파잘; 이성온
- Issue Date
- Feb-2024
- Publisher
- 한국로봇학회
- Keywords
- Segmentation; Deep Learning; Robotic Grasping
- Citation
- 로봇학회 논문지, v.19, no.1, pp 16 - 22
- Pages
- 7
- Indexed
- KCI
- Journal Title
- 로봇학회 논문지
- Volume
- 19
- Number
- 1
- Start Page
- 16
- End Page
- 22
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118408
- DOI
- 10.7746/jkros.2024.19.1.016
- ISSN
- 1975-6291
2287-3961
- Abstract
- Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.
Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF ENGINEERING SCIENCES > DEPARTMENT OF ROBOT ENGINEERING > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118408)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.