Hugging Face · Alio IT

RouteOptimizer

An open-source machine-learning model for mine fleet dispatch, plus A* and CBC solvers that still produce the proven plans.

Run in Colab Model card GitHub alioit.com

RouteOptimizer CLI: scenario file in, dispatch and shift plan JSON out

CLI demo: scenario JSON in → dispatch / shift-plan JSON out.

Install

pip install route-optimizer

# with samples from the GitHub repo:
git clone https://github.com/AlfonsoALIO/RouteOptimizer.git
cd RouteOptimizer
route-optimizer dispatch samples/tiny_feasible.json -o out/dispatch.json --segments 8 --trucks 2
route-optimizer shift-plan samples/tiny_feasible.json -o out/shift_plan.json --segments 4

What’s in the release

ML dispatch policy — small network that imitates A* among legal moves (~91% holdout vs ~56% greedy).
A* dispatch — truck movement plan over a shift.
MILP shift plan — PuLP + open-source CBC (no Gurobi/CPLEX).
MIT license — offline JSON I/O; no live telematics in this release.