물체 파지점 검출 향상을 위한 분할 기반 깊이 지도 조정
Segmentation-Based Depth Map Adjustment for Improved Grasping Pose Detection
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (20)
- B. Tekin, "Real-time seamless single shot 6d object pose prediction", 2018 IEEE, 2018, 292~301
- S. Peng, "Pvnet : Pixelwise voting network for 6dof pose estimation", 2019 IEEE, 2019, 4556~4565
- H. Han, "6-DoF grasp pose estimation based on instance reconstruction", Intelligent Service Robotics (2023)[DOI]
- J. Mahler, "Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics", Robotics: Science and Systems (2017)[DOI]
- D. Morrison, "Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach", Robotics: Science and Systems (2018)[DOI]
- D. Morrison, "Learning robust, realtime, reactive robotic grasping", The International Journal of Robotics Research, 39(2-3), pp.183~201 (2019)[DOI]
- S. Dodge, "Understanding how image quality affects deep neural networks", 2016 Eighth International Conference on Quality of Multimedia Experience(QoMEX), pp.1~6 (2016)
- J. Park, "High quality depth map upsampling for 3D-TOF cameras", 2011 International Conference on Computer Vision, pp.1623~1630 (2011)
- S. Wang, "Efficient fully convolution neural network for generating pixel wise robotic grasps with high resolution images", 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp.474~480 (2019)
- I. Lenz, "Deep learning for detecting robotic grasps", The International Journal of Robotics Research, 34(4-5), pp.705~724 (2015)[DOI]
- L. Pinto, "Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours", 2016 IEEE International Conference on Robotics and Automation (ICRA), pp.3406~3413 (2016)
- J. Redmon, "Real-Time Grasp Detection Using Convolutional Neural Networks", 2015 IEEE International Conference on Robotics and Automation(ICRA), pp.1316~1322 (2015)
- Z. Wang, "Robot grasp detection using multimodal deep convolutional neural networks", Advances in Mechanical Engineering, 8 (2016)[DOI]
- A. Depierre, "Jacquard: A large scale dataset for robotic grasp detection", 2018 IEEE, 2018, 3511~3516
- K. He, "Mask r-cnn", International Conference on Computer Vision(ICCV), pp.2980~2988 (2017)
- J. Kim, "Grasping Complex-Shaped and Thin Objects Using a Generative Grasping Convolutional Neural Network", Robotics, 12(2) (2023)[DOI]