AI-industrie.png

Smart Manufacturing & Materials-iStock-1135159658-BEWERKT.jpg

<p><strong>Every resident of Twente is familiar with them: the trucks from waste collection company Twente Milieu that drive through the streets to empty the green, orange, or gray mini-containers. To ensure that the garbage trucks empty the five million mini-containers collected annually as efficiently as possible, perfect route planning is essential. To achieve this, Twente Milieu enlisted a research team from the University of Twente. It was a fruitful collaboration that, through practical research, data, and algorithms, yielded even better collection routes.</strong></p><p><img src="https://cms.aihub-oost.nl/uploads/Optimale_route_vuilniswagen_dankzij_Universiteit_Twente_0ebed23974.png?token=mFQa23wC8ZjbBgPgTziNsTd9UfcUoCEDocD3PQDkk1I&amp;expires=1777451597" alt="Optimale route vuilniswagen dankzij Universiteit Twente.png" srcset="https://cms.aihub-oost.nl/uploads/thumbnail_Optimale_route_vuilniswagen_dankzij_Universiteit_Twente_0ebed23974.png?token=2g_sxAcpPw67LqYZyKD-hD49EH_B2WHTSY3SePw9VQE&amp;expires=1777451597 234w," sizes="100vw" width="320" height="213"></p><p>As Charles Vinke, managing director, and Remco Vriesema, operations and equipment manager at Twente Milieu, emphasize, the waste collection company’s route planners already had their routes well organized. “Our intuition told us, ‘We’re doing well, but we can’t be absolutely sure,’” Charles explains. “That’s why I asked Professor Richard Boucherie of the University of Twente for help.” Richard is a professor of Stochastic Operations Research and chair of the Data Science &amp; AI Lab and MKB Datalab Oost-Nederland, which use operations research and artificial intelligence (AI) to answer data-driven questions. They collaborate with regional companies and organizations such as AI-hub Oost-Nederland. MKB Datalab-Oost is an initiative of AI-hub Oost-Nederland, of which the University of Twente and Radboud University are partners.</p><h2>Pleasantly Surprised</h2><p>The professor was pleasantly surprised by the research question that Charles presented to him and his colleagues on behalf of Twente Milieu. “A question like this indicates that they’re on the right track as a company. That they’re leading the way. Something that was also confirmed over the course of the project,” says Richard. Twente Milieu not only had a question but was also open to clarifications from the University of Twente, the professor noted. “Our researchers Maik Overmars and Matthias Walter quickly realized that the central research question encompassed several components, such as the optimal distribution of trash collection days across neighborhoods to minimize the number of trash trucks needed, and the shortest driving routes for trash trucks within a neighborhood.’ Remco: ‘They collaborated extensively with our experienced staff members Raymond Degenhart and Jos Smook, who served as project leaders for this study.’</p><h2>Influences</h2><p>When creating an efficient route, planners must contend with external factors. For example, different restrictions apply in each municipality, as not every municipality has the same waste collection policy. “In addition, Twente Milieu uses two types of vehicles, each with its own capabilities and limitations: rear-loaders (garbage trucks where the mini-container is emptied from the rear) and side-loaders (trucks with a robotic arm on the side). A side-loader can empty containers on only one side of the street at a time, and in narrow streets, the Twente Milieu garbage trucks can’t always make the turn,” says Richard.</p><blockquote><p>A collaboration between science and practice</p></blockquote><p>On top of that, Twente Milieu collects each waste stream at a different frequency: “We collect vegetable, fruit, and garden waste (VFG) on a regular basis, whereas with pay-as-you-throw containers—for which residents pay per pickup—the number of containers placed curbside varies each time. These are all factors that influence our planning,” says Remco. Richard adds: “The enormous number of mini-containers—often several for different types of waste per address—makes figuring out ideal routes extremely challenging.”</p><h2>Operations research and AI methods</h2><p>The University of Twente developed a unique model that uses algorithms to calculate the optimal route for drivers. Richard: “The foundation is an automated map based on OpenStreetMap. Using data science and AI, we linked Twente Milieu’s database to it. This allows you to see, for each address, which mini-containers are available, as well as the applicable pickup days and the types of waste involved. By applying state-of-the-art insights from operations research, we then developed a mathematical algorithm to find the best route through a neighborhood within a reasonable computation time. We can also modify, remove, or add data. The algorithm then automatically recalculates the optimal routes.”</p><h2>Testing in Practice</h2><p>The theoretically ideal routes have been tested in practice. “We compared the existing routes—about a thousand in total—with the optimal routes calculated by our mathematical algorithm,” says Richard. Researcher Maik rode along on the garbage truck several times. Thanks to the research, Twente Milieu’s rear-loading trucks can now drive 10 percent fewer kilometers, and side-loading trucks 5 percent fewer. “Together, we’ve come very close to optimal routes. We can even deploy one fewer garbage truck per day. Another advantage is that this makes it easier and more efficient to schedule employees.”</p><blockquote><p>People and algorithms work together to find a better solution</p></blockquote><h2>More insights</h2><p>Remco is pleased with the confirmation provided by the study. “Our route planning was already good, and the study has given us insights to optimize it even further. In addition, thanks to the map, our planners now have a starting point should a new neighborhood be developed or a route adjustment be needed in the future.” Richard adds: “A planner still has to check whether a route that’s ideal in theory is actually ideal in practice; our model is a decision-support system. People and algorithms work together to arrive at a better solution. Our solution isn’t just applicable to Twente Milieu, but to all waste collectors in the Netherlands.’</p><h2>Scientific article</h2><p>Looking back, Richard reflects with great pleasure and enthusiasm on the collaboration with Twente Milieu. “The project is a wonderful example of how the co-creation of science and practice provides insight into practical issues. From the CEO to the garbage truck driver and from the planner to the researcher, everyone in this project contributed their knowledge and expertise. Not only did we deliver a solution for Twente Milieu, but we also wrote a scientific article about the mathematical model.’</p>

Garbage trucks follow the optimal route, thanks to a mathematical model developed by the University of Twente

These entrepreneurs have paved the way for you

Meet our frontrunners

Optimale route vuilniswagen dankzij Universiteit Twente.png

<p>Every resident of Twente is familiar with them: the trucks from waste collection company Twente Milieu that drive through the streets to empty the green, orange, or gray mini-containers. To ensure that the garbage trucks empty the five million mini-containers collected annually as efficiently as possible, perfect route planning is essential. To achieve this, Twente Milieu enlisted a research team from the University of Twente. This fruitful collaboration, combining practical research, data, and algorithms, resulted in even better collection routes.</p>