Lightweight Detection and Adaptive Path Planning for Selective Hotan Rose Harvesting
Jijing Lin, Yuhang Yang, Baojian Ma, Zhenghao Wu, Bangbang Chen · 2026
Read Lightweight Detection and Adaptive Path Planning for Selective Hotan Rose Harvesting by Jijing Lin, Yuhang Yang, Baojian Ma, Zhenghao Wu, Bangbang Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13165957.txt.
Description
Jijing Lin, Yuhang Yang, Baojian Ma, Zhenghao Wu, and Bangbang Chen build a robot eye and planner for picking roses, in a 2026 paper. Hotan roses serve two trades: buds for one, open blooms for another, so a picker must tell them apart. Farm computers are weak, so the vision model must stay light. Their trimmed model adds two custom parts to a standard tiny detector to sharpen its eye while cutting bulk.
The slim model named buds and blooms with high scores, at about half the size of the base model. A path planner then strings the picks into a short route, adapting to how crowded the scene is. Its routes ran far shorter than those from standard planners, and each plan took mere thousandths of a second. The authors say the pair brings careful picking within reach of cheap farm gear.
Catalog record
| CREATOR | Jijing Lin, Yuhang Yang, Baojian Ma, Zhenghao Wu, Bangbang Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |