vix.ing · top · new · best · stats · spec

Comparing State-of-the-Art and Emerging Augmented Reality Interfaces for\n Autonomous Vehicle-to-Pedestrian Communication

2021/02/04 by Filippo Gabriele Pratticò, Pratticò, F. Gabriele, Fabrizio Lamberti +7 · 2 citations
Computer Science · Engineering · Health Professions · Psychology · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Graphics (cs.GR) #Human-Automation Interaction and Safety #Human-Computer Interaction (cs.HC) #Older Adults Driving Studies #Traffic and Road Safety #Virtual Reality Applications and Impacts

paper · pdf · doi:10.48550/arxiv.2102.02783

openalex publication_date 2021/02/04 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

Providing pedestrians and other vulnerable road users with a clear indication\nabout a fully autonomous vehicle status and intentions is crucial to make them\ncoexist. In the last few years, a variety of external interfaces have been\nproposed, leveraging different paradigms and technologies including\nvehicle-mounted devices (like LED panels), short-range on-road projections, and\nroad infrastructure interfaces (e.g., special asphalts with embedded displays).\nThese designs were experimented in different settings, using mockups, specially\nprepared vehicles, or virtual environments, with heterogeneous evaluation\nmetrics. Promising interfaces based on Augmented Reality (AR) have been\nproposed too, but their usability and effectiveness have not been tested yet.\nThis paper aims to complement such body of literature by presenting a\ncomparison of state-of-the-art interfaces and new designs under common\nconditions. To this aim, an immersive Virtual Reality-based simulation was\ndeveloped, recreating a well-known scenario represented by pedestrians crossing\nin urban environments under non-regulated conditions. A user study was then\nperformed to investigate the various dimensions of vehicle-to-pedestrian\ninteraction leveraging objective and subjective metrics. Even though no\ninterface clearly stood out over all the considered dimensions, one of the AR\ndesigns achieved state-of-the-art results in terms of safety and trust, at the\ncost of higher cognitive effort and lower intuitiveness compared to LED panels\nshowing anthropomorphic features. Together with rankings on the various\ndimensions, indications about advantages and drawbacks of the various\nalternatives that emerged from this study could provide important information\nfor next developments in the field.\n

Citations

Cited by

Related