Reproduce “MRPoS: Mixed Reality-Based Robot Navigation Interface Using Spatial Pointing and Speech with Large Language Model” 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
Eduardo Iglesius, Masato Kobayashi, Yuki Uranishi
The authors present MRPoS, a mixed-reality system that lets users point to robot goal locations and speak mapped labels for facing directions, then displays the resulting beacons. In a study of 16 participants, MRPoS reduced three-destination beacon-generation time from 42.92 seconds with MRNaB to 17.88 seconds and lowered reported workload. These findings do not establish improved accuracy or usability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.