For transport companies, optimizing routes is a major challenge. And Transarc will not say otherwise! This transport specialist has long wondered how to efficiently improve the organization of its drivers’ rounds. Indeed, for each round, Transarc records several kilometers of empty transport from point A to point B. The coach drives but does not carry anyone, which is a pity. Transarc therefore contacted Neovision to find a solution.
To meet this challenge, Neovision developed a web application for Transarc to optimize rounds, named K Factor for Kilometers. By exchanging certain route/driver assignments, Transarc optimizes its routes and reduces empty running.
Thanks to the artificial intelligence used in the Factor K software, Transarc was able to make a profit of 200,000 kilometers, or €200,000 in one year on empty runnings. By adjusting the routes and switching some of them between drivers, Transarc obtained a ROI of 3 months. Beyond the financial aspect, the challenge was also environmental with less carbon emissions, and social with drivers spending less time alone in their coach.
Transarc is a road transport company, more specifically coaches. It has more than 700 vehicles and 16 depots in several regions of France (Grand-Est, Bourgogne-Franche-Comté and Auvergne Rhône-Alpes).
Empty runnings are a real issue and also have a substantial cost.
As good mathematicians, we are going to show you the problem… Thanks to Transarc, we know that a 1 km drive by a coach costs the company €1 (salary, fuel, taxes, wear and tear…) Patrick, bus driver at Transarc, does 10 km of empty running before getting to his first round. He then starts on his second round which is at the other end of the city (let’s say 6,54 km). He then goes on to three other rounds also far apart (1.2 km, 7 km and 2.6 km). The sun sets, he drops off his last passenger and drives 14 km to return to his depot. Overall, Patrick did over 41 km of empty running in one day, which cost Transarc €41. So if we make the following calculation:
So if we make the following calculation:
n empty km X x drivers X y days = too much money and a bad move for the environment!
Neovision therefore named K Factor the indicator for calculating this cost. It is the result of a difference between the optimal ERD (empty running distance) needed to do several rounds with the best depot and the actual ERD. But how do you get the optimal ERD? Well, by changing the depot location!
In order to best meet Transarc’s needs, Neovision first challenged its customer’s idea. Initially, the company wanted to calculate the optimal depot locations in order to know where to recruit. However, as it deepened its analysis, Neovision noticed that it was possible to go further by optimizing Transarc’s operations, with available resources, while recommending the right recruiting areas. Double shot!
To launch this project, Neovision first conducted a pre-study. This was followed by a study and software development phase. In 6 months, Transarc was able to integrate a functional AI solution allowing it to optimize its empty runnings. Since then, Neovision has been providing level 2 maintenance of the software for an always top-quality service. Level 1 maintenance is provided by Transarc’s IT department trained by Neovision.
Neovision’s goal was to minimize the K Factor to ensure better performance for Transarc. Neovision relied on OpenStreetMap, an open source mapping database for collecting location-based data (via GPS for example), and part of its third-party software ecosystem. Using these third party software, Neovision created an algorithm capable of calculating the K Factor by playing with the geographical positions of the depots and those of the different rounds. The goal was to exchange routes between drivers from different depots to obtain an optimal route.
To make the use of this tool more ergonomic for Transarc, Neovision then developed a web application called K Factor. It allows to visualize on a map, thanks to a color setting, the potential depots or to simulate the exchanges of rounds between drivers that one would like to make. After two months, Transarc was used to the tool and noticed that the visualization in the form of a map also enabled them to carry out an optimization they had not thought of: moving the depots of certain drivers
A few months later, in April 2019, French news channel TF1 highlighted the partnership of Transarc and Neovision in a report. TF1 praised the merits of the K Factor software and another project – in progress at the time – explaining the benefits of investing in artificial intelligence even for SMEs.
Patrick now wastes less time on empty runnings, less money in fuel and Mother Nature thanks him.
OPERATIONS RESEARCH, OPEN DATA, DJANGO, LEAFLET
«We were delighted to collaborate with the NEOVISION team on this very innovative project in the field of transportation. The specifications were met and the final results go beyond our initial expectations. If we had to highlight the team’s strong points I would say:
New projects are waiting for us and I can’t wait to get started! »
Damien Rameau, Manager of Transarc
16 October 2020
Applications Web, Cloud, Recherche opérationnelle