Case study · Mobility
Schedule an electric cab fleet automatically.
We built an AI-driven scheduler for an electric-cab fleet, solving many hard constraints at once with each cab's battery charge as a primary limit.
Engagement detail
The problem
An operator of a fleet of electric cabs needed to schedule a large set of planned pickup and drop trips efficiently, with each cab's battery charge as a primary constraint on which trips it could take. Every cab is either at a pickup depot or on the road via telematics, and assigning the best cab meant satisfying many simultaneous constraints: sufficient charge, driver hours, vehicle-type eligibility per campus, escort round-trip rules, occupancy limits, minimum wait times, even distance distribution across cabs, minimal dead miles, resilience to single-cab disruption, and charging around fast/slow requirements — all while maximising utilisation.
What we built
We solved the problem in two stages: exact mathematical programming for the core allocation, followed by heuristic methods — Genetic Algorithms, Tabu Search and Simulated Annealing — to handle the full complexity of real-world constraints at scale. The result is a fully optimised, automated scheduler built specifically for this fleet's operational rules.
Impact
- A fully automated, AI-driven scheduler replacing manual trip allocation.
- Multiple hard business and logical constraints solved simultaneously per allocation.
- Battery-aware, telematics-driven scheduling operating in real time across the fleet.
On sourcing. Every fact and figure here comes from Sail Analytics' project record for this engagement. Client names are withheld where they were not released for publication.
Have a problem like this?
Tell us the systems you're working with and what you can't currently see.