Multi-Path Routing Algorithm for Inclusive Mobility in an Urban Environment Hugo Machado ADiT-LAB Instituto Polit´ ecnico de Viana do Castelo, 4900-347 Viana do Castelo, Portugal hugomachado@ipvc.pt Sara Paiva ADiT-LAB Instituto Polit´ ecnico de Viana do Castelo, 4900-347 Viana do Castelo, Portugal sara.paiva@estg.ipvc.pt Ana I. Pereira CeDRI Polytechnic Institute of Braganc ¸a, 5300-253 Braganc ¸a, Portugal apereira@ipb.pt Abstract—The concept of smart city is frequently used nowa- days to refer to the level of integration of cities with citizen services. Mobility and navigation are some examples. When considering disabled users, in a temporary or permanent way, the challenges to provide such services in an efficient way are even bigger. This paper is an extension of a previous work where a mobile application to recommend the most suitable route for citizens was implemented with both Dijkstra and A-Star algorithms. The presented work describes a multi-path approach considering the user might want to choose several destinations in the mobile application and obtain the most suitable route that goes through all of them. Results are presented using the Genetic and the Simulated Annealing Algorithms. Both were evaluated with 100 runs and 2, 4, 8 and 16 destinations. The average algorithm execution time, standard deviation, median value, maximum and minimum execution times were assessed. The Simulated Annealing Algorithm presented better results and always suggested the shorter, or equal, path when comparing to the Genetic Algorithm. Index Terms - Inclusive Mobility. Routing Algorithms, Dis- abled People, Multi Path routing. I. I NTRODUCTION Currently, nearly 15% of the global world population have some type of disability that limits mobility [1]. The use of applications to support the mobility of citizens is a reality and majority of the cities [18]. These applications have more rele- vance for people with some kind of mobility disability due to the constant growth and changes that happen in the cities and that require accessibility reformulation. Therefore, the interest of developing newer and improved mobility applications has been growing exponentially, mainly with regard to assistance to people with permanent or temporary mobility disabilities [3]. Urban orientation is intrinsically linked to mobility and it refers to the ability of a citizen to know at every moment exactly where he is, whether or not he knows the city, and to be able to get directions to a desired location [4]. Permanent or temporary mobility disabilities includes several types of segments such as visually impaired people, wheelchair users, people with autism spectrum disorder, deaf people, pregnant ladies, elder or people with toddlers. For each of these segments, the concerns and precautions to take during a route are quite different. For visually impaired people, the lack or total absence of vision makes them less aware of what is happening around them. Adding the fact that they have limited or no access to positioning information using vision, all information given to them must be as precise as possible. Based on previous studies, people belonging to this segment should not be redirected to routes where emergency vehicles exist. On the other hand, when referring to people using a wheelchair, the main concerns are related with the type of surfaces on which they move and also the slope. In these cases, the preferred surfaces for mobility must be uniform, firm and smooth while generating adequate friction for a comfortable and stable ride [5]. In turn, when talking about people with autism spectrum disorder the main concerns are related to the bustle of the streets and here there is a need to avoid these types of places during a route. In previous works [6] [18], a mobile application named Viana+Acess´ ıvel was developed in order to assist disabled people to move around the streets of Viana do Castelo. The application allows the user to choose his segment and to receive a personalized route considering his current location and intended destination, using the A-Star algorithm. The main contribution of this paper is an extension of the initial work with a multi-path routing algorithm, considering that allowing the choice of a single destination might be limited in several scenarios. In this paper, several algorithms are used and tested to understand which one has a better performance in this situation. The paper is organized as follows: Section II presents related works associated to algorithms used by navigation applications as well as the current available applications. Section III briefly introduces the system, layout changes and evaluation. Section IV presents the conclusions and future work. II. RELATED WORK In this section, some algorithms that can potentially be used to implement the multi-path approach are presented and then some mobility aid applications are introduced. 2022 IEEE International Smart Cities Conference (ISC2) | 978-1-6654-8561-6/22/$31.00 ©2022 IEEE | DOI: 10.1109/ISC255366.2022.9921790 Authorized licensed use limited to: b-on: Instituto Politecnico de Viana do Castelo. Downloaded on November 27,2022 at 16:24:08 UTC from IEEE Xplore. Restrictions apply.