Reproduce “An Integrated Open-Source Stack for Vision-Based Autonomous Navigation of Wheeled Rovers” 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
Iaroslav Kolomiets, Iaroslav Sheipak, Mikhail Reppo, Vsevolod Egorov, Viktor Chertopolokhov, Isaac Chairez
The authors present an open-source ROS 2 stack that guides a rover from plain arrow markers to a cone and back. It links learned detection to localization, planning, mission logic, and rover-specific control. On 478 held-out images, YOLOv8n scored 0.68 [email protected] for arrows and cones versus OpenCV’s 0.23 and 0.05; three missions demonstrated integration but not reliability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.