A path-guided audio based indoor navigation system for persons with visual impairment Dhruv Jain, Akhil Jain, Rohan Paul, Akhila Komarika, M. Balakrishnan Assistive Technology Group, Department of Computer Science and Engineering Indian Insitute of Technology Delhi New Delhi-110016, India {cs1090187@cse, cs5110274@cse, rohan_paul, ee2080383@ee, mbala@cse}.iitd.ac.in ABSTRACT Independent path-based mobility in an unfamiliar indoor en- vironment is a common problem faced by visually impaired community. We present the design of an infra-red based active wayfinding system for the visually impaired. Our proposed system: downloads the floor plan of the build- ing, locates and tracks the user inside the building, finds the shortest path and provides step-by-step direction to the destination using voice messages. The audio instructions include active guidance for impending turns in the path of travel, distance of each section between turns, obstacle warn- ing instructions and position correction messages when the user gets lost. Results from a needs finding study with visu- ally impaired individuals formed the design of the system. We then deployed the system in a building and field tested it with users using a standardized before-and-after study. The comparison of the results demonstrated that the system is usable and useful. Categories and Subject Descriptors: K.4.2 [Comput- ers and Society]: Social Issues - Assistive technologies for persons with disabilities; C.3 [Computer Systems Orga- nization]: Special-Purpose and Application-Based Systems— Real-time embedded systems General Terms: Human Factors, Design, Experimenta- tion, Measurement 1. INTRODUCTION AND RELATED WORK Navigation and wayfinding to reach a desired destination is a considerable challenge for a visually impaired person par- ticularly in an unknown indoor environment. Path finding is a composition of several cognitive processes like map build- ing, landmark identification, obstacle avoidance and interac- tion with by-standers to ask directions. Most of the globally present signages are vision based and thus are inaccessible to them. Locating an accessible signage (tactile, audio) again poses a problem. Navigators currently rely on sporadic help from bystanders and use path integration to follow a given direction. This causes anxiety, embarrassment and makes them reluctant to go alone in an unfamiliar building. This was also corroborated in our own needs finding study. Existing commercial navigation systems based on GPS(eg. StreetTalk[1]) have made navigation a lot easier in outdoor environments. But their major shortcoming is that they can only identify very specific landmarks encountered by the user and typically do not work in the indoor setting. Several at- tempts have been made to address the problem of indoor navigation for visually impaired. However, no single solu- tion has found wide acceptability and long term deployment for use. Most of the systems present today are either only landmark identification systems with no path-based guid- ance(eg. RFID[4], Infrared based systems[2]) or are inaccu- rate for an indoor environment(eg. dead-reckoning[3], GPS). Few systems exists which are both omnipresent(which could localize the user accurately from any point in the building) and provide step-by-step path based wayfinding. Those who do meet both these criteria(eg. Building Navigator[5]), are very bulky to carry and expensive to operate. In this work, we present the design and implementation of a portable and self-contained indoor navigation system cur- rently deployed in a university building. Comprising of a network of wall mounted units and a user module coupled with a mobile application (Figure 1), the system downloads the map of the building, localizes the user in its vicinity, takes the destination as input from the user, and then helps him to independently navigate to his destination using step- by-step navigational instructions. The system was built via iterative feedback from visually impaired people at every stage from inception, specification to testing. Novel features of the system are: • Step-by-step path-based navigation with active guidance for turns and important landmarks in the course of travel • Continuous update on position awareness information cater- ing to a visually impaired person’s need particularly ob- stacle warning instructions and corrective directions when the user gets deviated • Minimalistic and universal user interface which does not interfere with other routine activities and can also be eas- ily operated easily by low-vision and sighted persons • Reduced anxiety in finding and maintaining an optimal (distance wise) path, thereby allowing faster movement towards the goal