A wearable virtual guide for context-aware cognitive indoor navigation

Abstract

In this paper, we explore a new way to provide context-aware assistance for indoor navigation using a wearable vision system. We investigate how to represent the cognitive knowledge of wayfinding based on first-person-view videos in real-time and how to provide context-aware navigation instructions in a human-like manner. Inspired by the human cognitive process of wayfinding, we propose a novel cognitive model that represents visual concepts as a hierarchical structure. It facilitates efficient and robust localization based on cognitive visual concepts. Next, we design a prototype system that provides intelligent contextaware assistance based on the cognitive indoor navigation knowledge model. We conduct field tests to evaluate the system's efficacy by benchmarking it against traditional 2D maps and human guidance. The results show that contextawareness built on cognitive visual perception enables the system to emulate the efficacy of a human guide, leading to positive user experience.

GazeNav

“…This kind of navigation forces the user to spend attention on the map instead of letting her interact with the environment (e.g., to avoid obstacles or enjoy the view). In recent years, researchers have tried to overcome these problems by introducing novel interaction methods [17,26,27,37,38]. There have been approaches to support navigation through play [1], using augmented reality [31], through auditory interfaces [9], or even through music [7].…”

Cognitive-inspired visual navigation system

“…We suspect that differences in cognitive load, incurred by the different types of navigation assistance, probably contributed to the absence of an effect of navigation assistance. Previous investigation has shown that cognitive load was higher for 2D map than for wearable assistance, which in turn was higher than for human guide (Xu et al, 2014).…”

“…We present assumptions on how different types of navigation assistance, and associated cognitive loads, influence scene memorability during navigation; how the presence of navigation information makes a particular scene more memorable; and how a location of a scene affects its memorability. For the purpose of this study, we refer to the cognitive load as the total amount of mental effort required from the participant during the navigation task (Xu et al, 2014).…”

“…Both types of assistance provide just-in-time information and require less effort from the participantscompared to the 2D map. However, earlier experimental evaluation in similar settings shows that users' cognition load was higher when they used the wearable virtual navigator (WVN) than when they were guided by a human usher (Xu et al, 2014). Therefore, even if wearable assistance and human guidance provide a similar form of assistance, higher cognitive loadassociated with the WVN assistancemay reduce participants' visual memory performance.…”

“…An earlier experiment evaluated the users' cognitive loadhow much mental effort the subject has to make to complete the taskexperienced while using different types of navigation assistance compared in our study (Xu et al, 2014). The mean scores of the cognitive load, obtained from 7 levels Likert scale 5 , were as follow: MAP = 4.71; WVN = As different types of assistance do not affect scene memorability, the remaining results are presented without distinguishing which of them was used.…”