Ridesharing and Crowdsourcing for Smart Cities: Technologies, Paradigms and Use Cases

Abstract

Recent technology developments and the numerous availabilities of mobile users, devices and Internet technologies together with the growing focus on reducing traffic congestion and emissions in urban areas have led to the emergence of new paradigms for ridesharing and crowdsourcing for smart cities. Compared to carpooling approaches where the driver and participant passengers or riders are usually prearranged and the journey details known beforehand, the paradigm for ridesharing requires the participants to be selected at short notice and the rider trips are often dynamically formed. Crowdsourcing techniques and approaches are well suited to match drivers and riders for these dynamic scenarios, although there are many challenges to be addressed. This paper aims to survey this new paradigm of ridesharing and crowdsourcing for smart city transportation environments from several technological and social perspectives including: 1) ridesharing and architecture in transportation; 2) techniques for ridesharing; 3) artificial intelligence for ridesharing; 4) autonomous vehicles and systems ridesharing; and 5) security, policy and pricing strategies. The paper concludes with some use cases and lessons learned for the practical deployment of ridesharing and crowdsourcing platforms for smart cities.

Keywords

• Artificial intelligence
• crowdsourcing
• deep learning
• machine learning
• ridesharing
• transportation