Quote of the day

A person who never made a mistake never tried anything new.

- Albert Einstein

Contact

Deep Reinforcement Learning for Last-Mile Routing in Dense Historic Urban Fabrics

Open Logistics & Supply Chain

Deep Reinforcement Learning for Last-Mile Routing in Dense Historic Urban Fabrics

Deep Reinforcement Learning for Last-Mile Routing in Dense Historic Urban Fabrics

Description

Optimize last-mile delivery routes in dense pedestrian networks where conventional vehicles cannot operate by combining reinforcement learning with two-echelon transshipment constraints.

Details

Context and Problem Statement

Classical vehicle-routing models assume road accessibility and relatively stable travel times. Historic medinas often require transshipment to pedestrian or low-capacity modes, with variable congestion and restricted access.

Research Question

Which learned policy formulation best handles the joint assignment of shipments to transshipment points and sequencing of pedestrian routes under uncertain travel times?

Proposed Approach

Formulate a two-echelon routing problem and solve it with an attention-based reinforcement-learning policy. Compare against metaheuristics, estimate pedestrian travel times from GPS and network topology, and incorporate time-dependent congestion.

Expected Contribution

A realistic benchmark for dense historic urban logistics and a rigorous comparison of learned and classical optimization methods.

Expected Prototype

A route planner generating courier itineraries and supporting intra-day replanning after delays or failed deliveries.

Datasets

OpenStreetMap, standard routing benchmarks, and anonymized delivery traces from a partner operator.

Challenges

Incomplete pedestrian maps, stochastic travel times, informal access constraints, and cross-city generalization.

Research Question

Can a learned routing policy outperform classical metaheuristics for two-echelon delivery in dense stochastic pedestrian networks?

Innovation

The project formalizes a real logistics problem largely absent from mainstream benchmarks: delivery in non-vehicle-accessible historic urban environments.

Expected Deliverable

An open benchmark dataset, a trained routing policy, and a demonstrable planner with online replanning.

Technologies

Deep Reinforcement Learning and Attention-Based Policies Combinatorial Optimization and Metaheuristics GIS and OpenStreetMap Travel-Time Estimation Online Replanning

Required Skills

  • Operations Research and Combinatorial Optimization
  • Reinforcement Learning
  • Geomatics and Spatial Data Processing
  • Software Development

Datasets

  • OpenStreetMap pedestrian network
  • Standard vehicle-routing benchmark instances
  • Anonymized delivery traces from an operator

Morocco & Africa Relevance

Historic medinas in Morocco and North Africa concentrate commercial activity in networks inaccessible to standard delivery vehicles, making this problem regionally distinctive and highly relevant.