Discovering stop and parking behaviors of last mile delivery vehicles for urban areas based on not well conditioned GPS traces, expert knowledge and machine learning

Abstract

Nowadays urban traffic is one of the most serious challenges for local authorities around the world. This challenge implies issues regarding health, energy, safety, environment and quality of life. Achieving a fair traffic outcome is a key priority for city traffic managers while maintaining city’s attractiveness for citizens and travelers and those carrying out commercial activities. As a part of this challenge, delivery and similar companies are relevant stakeholders in optimizing their routes, deliveries, and operational services. It is in this respect that urban traffic and its regulations play a key role. The conditions in which urban traffic takes place thus have to be known and one way to deal with this is based on available and accessible data. In the IoT age, there could be huge amounts of available data generated by countless sensors and systems involved in our lives, cities, infrastructures, etc.... Taking advantage of such data, when the accessibility and quality is good enough, can help us to achieve the desired goals concerning the urban traffic and its consequences. However, in practice, the availability and access to such data is currently a very serious challenge.

Following on with this, data generated from the ever-increasing number of sensors on board vehicles could be very useful, not only for checking the vehicle condition, but also to gain a better of the “real-time” traffic situation or to discover traffic behaviors/patterns from the said data. In this work, a real case based study has been carried out gathering basic real GPS information regarding delivery vehicles in a city environment and OpenData to “discover” where, when and how long time delivery vehicles use the regulated parking zones for loading/unloading in the city center. Based on Expert Rules, a stop detection criteria is defined and formulated to be applied to real cases in urban areas, focusing on city centers and Machine Learning techniques to discover stop and park behaviors on last mile deliveries in a real urban area. All this is used to plan traffic strategies and facilities which can permit better and more fluent services. On the other hand, the results provide invaluable knowledge support for the expert knowledge of mobility managers, while also supplying new “findings” about the daily challenges, showing that machine learning techniques and other linked technologies are powerful tools for this challenge.