New ways to manage electric robotaxi fleets using battery levels
Managers can improve performance by making decisions based on a vehicle's state of charge.
Electric robotaxis are moving from pilots to scaled commercial deployment. These vehicles require centralized fleet control and careful management of state of charge (SoC).
Researchers studied how a manager should make service, empty repositioning, idling, and charging decisions. They used a continuous-time fluid model to track vehicles across location-charge states.
The study identifies two forms of charge-aware control. These are early return-to-depot (RTD) and charge-aware repositioning.
The optimal solution uses simple threshold structures. Each location has a battery threshold for when vehicles should return to the depot to recharge.
Vehicles should not return to the depot if their SoC is above the threshold. Above this threshold, the destination depends on whether the SoC matches the destination's battery sensitivity.
A case study using 2025 NYC Taxi and Limousine Commission trip records shows charge-aware control can generate substantial gains. Simple threshold-based heuristics recover most of the value of the fully charge-aware solution.
Key facts
- Charge-aware control includes early return-to-depot and charge-aware repositioning.
- The performance gap between charge-aware and charge-oblivious policies can be unbounded.
- A case study used 2025 NYC Taxi and Limousine Commission trip records.