Reproduce “AgriSense: Vision-Language Decision Support and Robotic Intervention in a Virtual Greenhouse Copy title” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Lyes Saad Saoud, Oualid Doukhi, Reza Ghorbani, Moussa Ayyash

AgriSense tests a proposal interface for greenhouse robots in a virtual environment, with a learned model predicting environmental references, a target zone, and an intervention proposal while separate controllers handle execution. On a source-grouped test set from one episode, full, image-removed, language-removed, and sensor/current-zone-only models each classify 43 of 44 target zones correctly, without establishing multimodal benefit or treatment validity.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.