Objectives
The project objectives cover the full cycle: development, field validation and replicability.
- Develop a pre-industrial AI/ML engine for logistics decision support, based on a modular architecture.
- Integrate the engine with the Power BI platform for results visualization.
- Validate a TRL 6 Proof of Concept on a real operational use case.
- Integrate an ESG module to quantify and simulate environmental impact.
- Build a replicable methodology for other medium-sized logistics operators.
- Transfer technical expertise to the client through workshops and training materials.
Initial Challenge
While large global logistics operators have developed sophisticated planning tools in-house, medium-sized companies are still largely excluded from access to such capabilities. As a result, operational decisions — how many vehicles to deploy, which routes to select, how to organize the fleet — are often based on experience alone, without the possibility of testing alternatives before implementing them.
The data needed to support these decisions already exists. The challenge is that it is typically fragmented across TMS, WMS and ERP systems that do not communicate with one another. This makes it difficult both to analyze current performance and to meet the ESG/CSRD reporting requirements increasingly required by regulation.
Solution
LogisticAI provides a modular decision engine that integrates real operational data and AI/ML techniques to support logistics planning. At the core of the system is an optimization solver based on the VRPTW formulation, implemented using Google OR-Tools.
The engine offers two analysis modes:
- What-If Simulation: modification of key parameters and recalculation of the optimal plan against the baseline.
- Find Optimal Value: identification of the optimal value through parametric sweep analysis.
A dedicated ESG module quantifies the emissions associated with each scenario according to the GLEC and CSRD frameworks. The results feed into a Power BI dashboard for the visualization of KPIs, maps and scenario-vs-baseline comparisons.
Benefits
The project generates measurable benefits across three areas: operational efficiency, sustainability and decision governance.
- Measurable reduction in kilometres travelled, operating costs and CO₂ emissions while maintaining the same service level.
- Greater decision transparency: each scenario is quantified, comparable and auditable.
- Built-in ESG/CSRD compliance through a dedicated module aligned with the GLEC framework.
- Reduced dependence on individual expertise for critical operational decisions.
- Integration with the existing visualization stack, Power BI, with no additional learning curve.
- Replicability: the methodology can be applied to other medium-sized logistics operators within the cooperative ecosystem.
For further information, please contact: projects@ifabfoundation.org.
