Developing, Implementing, and Verifying the Integrity of an Indoor Navigation System for Visually Impaired People

据估计，全球有2.5亿视力受损人士（Ackland\_et\_al\_2017），其中许多人使用手杖帮助他们四处走动。最常见的一种拐杖，被称为“长手杖”，是由视力极度受限或没有视力的视力受损人士使用的，以帮助他们找到路并避开障碍物。然而，长手杖只能探测到膝盖以下的障碍物，并且距离使用者大约1米。这使得视障人士在繁忙的城市地区安全导航尤其困难，尤其是在汽车、自行车和行人近在咫尺的地方。为了应对这一挑战，WeWALK开发了一种革命性的“智能”设备，可以固定在用户现有的手杖上。我们的手杖可以检测障碍物(例如：与用户的智能手机（Android/Apple）唯一连接，通过与谷歌地图的集成提供基于音频的导航。然而，我们现有的基于GPS的音频导航不能在室内使用，也不能提供足够高的空间分辨率和可信度（完整性），以帮助视障人士独立导航室内城市空间，如交通枢纽和购物中心。最近的室内导航系统依赖于检测从安装在室内空间的“信标”传输的蓝牙信号。智能手机和其他支持蓝牙的设备可以检测到信标信号，并可用于定位用户，例如，当他们接近自动扶梯、检票口和平台时，可以向他们发出警告。自2015年以来，这种信标已经在伦敦交通局进行了试验。然而，到目前为止，他们还没有展示出足够的系统性能（准确性/可靠性/可用性），用于安全关键应用，例如仅使用信标信号就能使视障用户在地铁站周围导航，避免危险。在这里，WeWALK与Astra-Terra（伦敦一家专注于智能交通系统的中小企业）、伦敦帝国理工学院交通研究中心和皇家国家盲人研究所合作，将解决阻碍室内导航广泛采用信标的技术/安全挑战。我们将通过开发一种新的完整性监控层（提供安全关键功能）和可用性框架，在现有信标安装基础和可用开放标准的基础上，直接用我们的智能手杖检测信标信号，以提供高精度、基于转弯的室内音频导航。这个项目有可能在确保越来越多的视障人士充分进入我们生活、工作和娱乐的城市空间方面发挥至关重要的作用。

There are an estimated 250million visually impaired individuals worldwide(Ackland\_et\_al\_2017), many of whom use a cane to help them get around. The most familiar type of cane, known as a "long cane", is used by visually impaired individuals with extremely restricted or no vision to help them find their way and avoid obstacles. However, a long cane can only detect obstacles below knee height and within approximately 1 m of the user. This makes it particularly challenging for visually impaired individuals to navigate safely in busy urban areas, especially where cars, bicycles, and pedestrians are found in close proximity.To address this challenge, WeWALK have developed a revolutionary "smart" device that screws onto a user's existing cane. Our cane detects obstacles(e.g.,trees) at knee-to-head height and uniquely connects to a user's smartphone(Android/Apple) to provide audio-based navigation via integration with Google Maps.However, our existing audio-based navigation relying on GPS cannot be used indoors and does not provide sufficiently high spatial resolution with the level of confidence(integrity) required to help visually impaired individuals independently navigate indoor urban spaces such as transport hubs and shopping centres.Recent indoor navigation systems rely on detecting Bluetooth signals transmitted from "beacons" installed across an indoor space. Beacon signals are detected by smartphones and other Bluetooth-enabled devices and can be used to locate the user, warning them, for example, when they are approaching escalators, ticket barriers, and platforms. Such beacons have been trialled with Transport for London since 2015\. However, to date, they have not demonstrated adequate system performance(accuracy/reliability/usability) for use in a safety-critical application such as enabling a visually impaired user to navigate, avoiding hazards, around a tube station using beacon signals alone.Here, WeWALK in collaboration with Astra-Terra (a London-based SME specialising in intelligent transportation systems), the Centre for Transport Studies at Imperial College London, and the Royal National Institute for the Blind will address the technical/safety challenges that have prevented widespread uptake of beacons for indoor navigation. We will build on the existing installed base of beacons and the available open standard by developing a novel integrity-monitoring layer (providing safety-critical functionality) and usability framework, detecting the beacons signals directly with our smart cane to provide high-accuracy, turn-by-turn indoor audio-based navigation. This project has the potential to play a vital role in ensuring that the rising numbers of visually impaired people have full access to the urban spaces where we live, work, and play.