Less is More: Generating Grounded Navigation Instructions from Landmarks [article]

Su Wang, Ceslee Montgomery, Jordi Orbay, Vighnesh Birodkar, Aleksandra Faust, Izzeddin Gur, Natasha Jaques, Austin Waters, Jason Baldridge, Peter Anderson
<span title="2022-04-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes. Existing generators suffer from poor visual grounding, causing them to rely on language priors and hallucinate objects. Our MARKY-MT5 system addresses this by focusing on visual landmarks; it comprises a first stage landmark detector and a second stage generator -- a multimodal, multilingual, multitask encoder-decoder. To train it, we bootstrap grounded landmark annotations on top of
more &raquo; ... e Room-across-Room (RxR) dataset. Using text parsers, weak supervision from RxR's pose traces, and a multilingual image-text encoder trained on 1.8b images, we identify 971k English, Hindi and Telugu landmark descriptions and ground them to specific regions in panoramas. On Room-to-Room, human wayfinders obtain success rates (SR) of 71% following MARKY-MT5's instructions, just shy of their 75% SR following human instructions -- and well above SRs with other generators. Evaluations on RxR's longer, diverse paths obtain 61-64% SRs on three languages. Generating such high-quality navigation instructions in novel environments is a step towards conversational navigation tools and could facilitate larger-scale training of instruction-following agents.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12872v4">arXiv:2111.12872v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ictdllrge5fcrhfqlztzkq6ovq">fatcat:ictdllrge5fcrhfqlztzkq6ovq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220516030130/https://arxiv.org/pdf/2111.12872v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/47/12/47126c012d174d2c66dc99472d8b8f4333248ac7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12872v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>