Conference proceeding
ROG-Grasp: Root-Oriented Geometry for Robotic Grasping and Placement
IEEE International Conference on Automation Science and Engineering (CASE), pp 1562-1567
17 Aug 2026
Abstract
Orientation-aware manipulation is essential in post-harvest agricultural processing, where produce must be grasped and placed in consistent configurations. This paper presents ROG-Grasp, a geometry-based robotic grasping and placement framework that estimates the produce orientation from root surface geometry using RGB-D perception. A YOLO-based root detector and point cloud plane fitting are used to infer the root normal, enabling stable grasp pose generation and orientation-constrained Cartesian motion planning. Experiments on tomatoes and onions demonstrate high success rates and stable execution time in both isolated and cluttered scenarios. Compared with vision-language-action (VLA) policies, the proposed method achieves more reliable and accurate grasp completion with faster execution. These results highlight the effectiveness of geometry-driven perception for practical orientation-controlled manipulation tasks. A video of our paper is available online.
Metrics
1 Record Views
Details
- Title
- ROG-Grasp: Root-Oriented Geometry for Robotic Grasping and Placement
- Creators
- Zijian An - Drexel University, Electrical and Computer EngineeringAugustus Sroka - Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA,19104Ran YangBill Cai - Drexel UniversitySatoru Eto - Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA,19104Brian Poon - Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA,19104Kelvin Cai - Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA,19104Shijie Geng - Amazon (United States)Feng Liu - Drexel University, Computer ScienceYiming Feng - Virginia Seafood Agricultural Research and Extension Center,Department of Biological Systems Engineering,Hampton,VA,USA,23669Lifeng Zhou - Drexel University, Electrical and Computer Engineering
- Publication Details
- IEEE International Conference on Automation Science and Engineering (CASE), pp 1562-1567
- Conference
- 2026 IEEE 22nd International Conference on Automation Science and Engineering (CASE) (Shenyang, China, 17 Aug 2026–21 Aug 2026)
- Publisher
- IEEE
- Number of pages
- 6
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; Computer Science
- Other Identifier
- 9798319541581; 991022238553304721