Generating Contextually-Relevant Navigation Instructions for Blind and Low Vision People
Navigating unfamiliar environments presents significant challenges for blind and low-vision (BLV) individuals. In this work, we construct a dataset of images and goals across different scenarios such as searching through kitchens or navigating outdoors. We then investigate how grounded instruction generation methods can provide contextually-relevant navigational guidance to users in these instances. Through a sighted user study, we demonstrate that large pretrained language models can produce correct and useful instructions perceived as beneficial for BLV users. We also conduct a survey and interview with 4 BLV users and observe useful insights on preferences for different instructions based on the scenario.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning
Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task navigation guided by complex, long-horizon language instructions. Current vis…
iMotion-LLM: Motion Prediction Instruction Tuning
We introduce iMotion-LLM: a Multimodal Large Language Models (LLMs) with trajectory prediction, tailored to guide interactive multi-agent scenarios. Different from conventional motion prediction approaches, iMotion-LLM c…
Autonomous Navigationmotion predictionPredictionTrajectory PredictionAn Efficient Indoor Navigation Technique To Find Optimal Route For Blinds Using QR Codes
Blind navigation is an accessibility application that enables blind to use an android Smartphone in an easy way for indoor navigation with instructions in audio form. We have proposed a prototype which is an indoor navig…
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM
Vision-and-Language Navigation (VLN) is an essential skill for embodied agents, allowing them to navigate in 3D environments following natural language instructions. High-performance navigation models require a large amo…
NavigateRAGRetrievalRetrieval-augmented Generation+3Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem
Car-focused navigation services are based on turns and distances of named streets, whereas navigation instructions naturally used by humans are centered around physical objects called landmarks. We present a neural model…
Natural Language Landmark Navigation Instructions Generation