Large scale collaborative logistics optimization by artificial intelligence

Large scale collaborative logistics optimization by artificial intelligence
DeustoTech ( is a private non-profit institution of the Faculty of Engineering at the University of Deusto for applied research in new technologies. Since 2005 DeustoTech mission is to support the ICT activity in business and society through research, the development of technologies, innovation and knowledge transfer. We focus our activity around TRLs 2-7 and articulate it into four applied fields. We are characterized for working with data of heterogeneous nature, throughout its life cycle and in compliance with ethical principles and humanists who define the University of Deusto. Within the University of Deusto and DeustoTech, the scientist in charge participates in the Mobility Research Unit. The unit is actively participating and coordinating several H2020 projects such as TIMON (2015-2018, GA:636220 ; ), POSTLowCIT(2016-2019, GA: 2015-ES-TM-0239-S, and LOGISTAR (2018-2021, GA: 769142, In addition to this, the research unit is highly active in international forums, being part of ECTRI, the European research association for sustainable and multimodal mobility, a European platform involving all the most outstanding research centres in transport ( Apart from the research group, for the development of this project, we will count with the support of external collaborators, with which we have an active relationship.
We are looking for post-doctoral researchers with a strong background in metaheuristics, or related optimization methods. The candidate must have a proven track record on publications in journals and conferences related to these areas. The candidate must have good programming skills and must prove enough independence to program their own methods. Knowledge and experience in programming languages, like Python or Java, is a requirement. Knowledge about some distributed computing frameworks as Apache Spark, Tensorflow, Pytorch, etc is also desirable. Additionally, experience in research projects will be welcome, particularly in H2020 or similar international programmes. Researchers with experience in the application of metaheuristics and modelling of optimization problems in the following fields will be especially welcomed: vehicle routing, supply chain, transhipment, logistic systems.
  • Information Sciences and Engineering (ENG)
Statistics show a problem with transport efficiency in Europe: that vehicles are operating partially filled. EU statistics show a range of between 24% and 28% empty vehicle running, and capacity utilisation by weight ranging from 54% to 57%, over the latest 10 years period. Together these two observations result in an overall efficiency score of European road transport of around 45%. Horizontal collaboration among different companies is one of the most promising approaches to deal with this issue. It consists of the collaboration among two or more firms at the same level of the supply chain by sharing resources, operations, etc. The research proposed is related to the optimization of this horizontal collaboration. The first objective aims at developing richer optimization models that combine interdependent problems to improve the applicability of the solutions in a real environment. The second objective consists on the design of these models according to the robust optimization paradigm to provide solutions adapted to the risk aversion of the decision-maker. The third objective entails the development of high-performance and robust methods by the hybridization among different metaheuristic classes or metaheuristics with other techniques, on one hand; and on the other hand, to create highly scalable and efficient optimization algorithms leveraging new distributed computation paradigms and using a design that facilitate its deployment in cloud platforms at a big scale.


E. Osaba, R. Carballedo, F. Diaz, E. Onieva, A.D. Masegosa, A. Perallos. Good practice proposal for the implementation, presentation, and comparison of metaheuristics for solving routing problems. Neurocomputing 271: 2-8, 2018 Journal JCR Ranking: 24/133(Q1); Google Scholar Citations: 4 E. Osaba, X. S. Yang, F. Diaz, E. Onieva, A. D. Masegosa, A. Perallos. A discrete firefly algorithm to solve a rich vehicle routing problem modelling a distribution system with recycling policy. Soft Computing-A Fusion of Foundations, Methodologies and Applications, 21(18): 5295-5308, 2017 P. Lopez-Garcia, E. Onieva, E. Osaba, A. D. Masegosa, A. Perallo. GACE: A meta-heuristic based in the hybridization of Genetic Algorithms and Cross Entropy methods for continuous optimization. Expert Systems with Applications, 55, 508-519, 2016 E. Onieva, E. Osaba, I. Angulo, A. Moreno, A. Bahillo and A. Perallos, «Improvement of Drug Delivery Routes Through the Adoption of Multi-Operator Evolutionary Algorithms and Intelligent Vans Capable of Reporting Real-Time Incidents,» in IEEE Transactions on Automation Science and Engineering, 14( 2): 1009-1019, 2015 E. Onieva, U. Hernandez-Jayo, E. Osaba, A. Perallos, X. Zhang, A multi-objective evolutionary algorithm for the tuning of fuzzy rule bases for uncoordinated intersections in autonomous driving, Information Sciences, 321: 14-30, 2015.
MOMENTUM: Modelling Emerging Transport Solutions for Urban Mobility. European Union’s H2020 Programme. Topic LC-MG-1-3-2018: Harnessing and understanding the impacts of changes in urban mobility on policy making by city-led innovation for sustainable urban mobility [Grant Agreement]. Coordinating Institution: EMT Madrid S.A. Total budget consortium: 2,927,875€. Total budget host unit: 204,000€. Duration: 2019 – 2022. LOGISTAR: Enhanced data management techniques for real time logistics planning and scheduling. H2020 programme – MG-5.2-2017: Innovative ICT solutions for future logistics operations [Grant Agreement 769142], Funding consortium: 4.997.548,75€. Funding host unit: 811.000€. 2018 – 2021, Coordinator: University of Deusto Low noise and low carbon freight delivery for Postal Operators to ensure last mile connections through optimized urban and long-distance transport (PostLowCIT), CEF Transport Programme, European Comission, 2015-ES-TM-0239-S, Funding consortium: 1.033.273€, Funding host unit: 302.925€, 2016 – 2019, Coordinator: Correos TIMON: Enhanced real-time services for optimized multimodal mobility relying on cooperative networks and open data. H2020 – MG-3.5a-2014 – Cooperative ITS for safe, congestion-free and sustainable mobility [Grant Agreement – 636220], Funding consortium: 5.605.213 €, Funding group: 943.750€, 2015 – 2018, Coordinator: University of Deusto


The research posed in this thesis is located on the intersection among two knowledge areas, Intelligent Transportation Systems and Artificial Intelligence. Below, we briefly describe these areas: Intelligent Transport Systems (ITSs): According to the EU Directive 2010/40/EU, ITSs are advanced applications which without embodying intelligence as such aim to provide innovative services relating to different modes of transport and traffic management and enable various users to be better informed and make safer, more coordinated and ‘smarter’ use of transport networks. ITSs integrate telecommunications, electronics and information technologies with transport. Artificial Intelligence: This discipline can be seen as a group of methodologies that aim at performing tasks that are usually assumed for humans as Natural Language Processing, Speech Recognition, Reasoning, etc. In this project, the MSCA research will mainly focus on Logistics, a subarea of Intelligent Transportation Systems that refers to the process of coordinating and moving resources – people, materials, inventory, and equipment – from one location to storage at the desired destination. In addition, optimization methods, a subfield of Artificial Intelligence that has experienced great advances in the last decade, and with the posibility of shaping the Logistics of the future. In particular, meta-heuristic approaches will be studied, which have shown great potential in the resolution of real cases.
Interdisciplinary will be achieved by the inclusion of the candidate in the operation of on-going projects in the field of logistics, such as those cited previously. Within those projects, the candidate will have the possibility to interact with real potential clients for the developments as well as providers of real problems to face during the hosting.


The research proposed in this thesis is aligned with the H2020 societal challenge on Smart, Green and Integrated Transport, especially with two of its key objectives: Better mobility, less congestion, more safety and security. As will be explained below, the research done in this work could contribute improve the mobility of goods. Global leadership for the European transport industry. The research proposed here would help to improve the design, planning and reliability of European distribution networks, and therefore to the global leadership of the European transport industry.


Within the framework of the on-going projects, as well as future ones, the candidate will interact with stakeholders in the logistic field, who provide him with data and real operational challenges. This collaboration will be continuous on time, by means of periodicals meetings for definition of requirements and presentation of results.


Successful Logistic operation depends on available resources and underlying dynamic variables. Changes can have significant effects across the entire network, causing delays and requiring recourse actions which significantly compromise efficiency, including repeated delivery attempts and underloaded vehicles. Industry practice relies on historical data to predict demand cycles, congestion rates, workforce availability or travel times. This tends to treat each aspect as independent, and is not responsive to real-time events. Most operations rely on human monitoring of event streams, and human-to-human negotiation to respond to change. Fundamental techniques have been developed, but rarely applied to logistics operation. For optimization models, the aim is twofold. First, to develop richer optimization models that combine interdependent problems to improve the applicability of the solutions in a real-environment, and second, design these models according to the robust optimization paradigm to provide solutions adapted to the risk aversion of the decision-maker. With respect to optimization algorithms, the aim is to methods by the hybridization among different metaheuristic classes or metaheuristics with other techniques, on one hand; and on the other hand, to create highly scalable and efficient optimization algorithms leveraging new parallel computation paradigms and using a design and an implementation that facilitate its deployment in cloud platforms at a big scale.


There are several methods, products and services for route planning and logistics operation management. But there is not a single product in the market focus in the area of the collaborative logistics, where different stakeholders may share information in order to get benefit from the potenctial pooling of resources, reducing so empty space in vehicles and empty kilometres, enabling to consolidate freights among different stakeholders.


One of the University of Deusto’s key duties is to be fully aware of problems within the institution itself and the society we live in. For this reason, it should take specific steps to boost integration and real equality of opportunity for people with specific support needs. Timely specific action is required to enable them to enter higher education in equal conditions and ensure their full integration in the university community. DeustoTech, as one of its institutions, is included into this service of social action and inclusion. The main aims consist of achieving full normalisation, equal opportunities and gradually adopting the steps needed to ensure that the University of Deusto is an inclusive educational institution. Furthermore, the University of Deusto provides them with guidance and support on the transition to the labour market jointly with special job centres and companies at large.