Multimodal travel sharing algorithm

• Grant number: 20/13848-1
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: December 01, 2021
• End date: August 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computational Mathematics
• Principal Investigator: Domingos Soares Neto
• Grantee: Domingos Soares Neto
• Company: Bynd Serviços de Tecnologia Ltda
• CNAE: Desenvolvimento e licenciamento de programas de computador customizáveis ; Desenvolvimento e licenciamento de programas de computador não-customizáveis
• City: São Paulo

Abstract

In large Brazilian cities as well as in several other cities around the world, the car is the preferred mean of transportation for getting around. However, most car trips are made with a single occupant, the driver. The average vehicle occupancy rate in a city like São Paulo is only 1.4 people, which means that in most cases only 20 to 25% of the vehicle's capacity is used. This inefficient transport choice brings negative externalities with traffic congestion. Car circulation represents about 70% of pollution in a large city and is a major source of stress for its citizens. Losses are also felt from an economic point of view. Studies show that Brazil loses approximately R$ 267 billion every year due to inefficiencies related to traffic. Within this context, companies in general are responsible for moving millions of people in a daily basis. According to the World Resources Institute (WRI), work-related trips represent approximately half of all trips in a city. The inefficiency observed in general traffic also applies to corporate travel. Corporate mobility policies are still quite incipient and offer great opportunities for optimization. Among the problems that arise frequently we can mention the occurrence of employees using individual transport to go to the same places, use of charters below capacity and idle fleets. These problems also cause direct economic losses to these companies. Given the great impact that corporate mobility has on the dynamics in the city, searching for more efficient and sustainable ways to transport employees is crucial to move towards smarter cities with a higher quality of life. This project aims to demonstrate the technical feasibility and optimization potential of a prototype of an integrated multimodal corporate mobility system, which uses machine learning algorithms to suggest, for each employee and in real time, the most efficient transport to a determined route, possibly combining different modes of transportation and possibilities of sharing between users, in order to minimize travel time, route deviation and travel cost. An optimization algorithm will be developed and tested to map the best available modal options, in real time, for the displacement of employees, performing the combination of compatible routes for the sharing of transport between users and also the combination of different options in the same route such as walking, public transit, transportation apps and carpool to make the most efficient arrival at the destination feasible, whether traveling from home to work or on occasional professional trips. For the construction of the prototype, the development of the multimodal sharing optimization algorithm will be integrated with the development of a mobile application that allows users to access the solution. With the execution of this project, the aim is to verify the technical feasibility and optimization potential of a multi-modal shared travel algorithm that is easily accessible through a mobile interface in an integrated multi-modal system for corporate mobility. If its viability and optimization potential is confirmed, it is expected to increase the efficiency of commutes and professional trips with more intelligent transport choices, generating results such as: reduction of expenses with corporate mobility; reduction of travel time for employees; reduction of carbon emissions related; greater perception of the well-being of users when commuting. (AU)