Electric ride-pooling improves service with smarter charger and route management
L2R-EV: Learning What to Repair in Electric Ride-Pooling with Finite Charger Queues
Computer Science and Game Theory
Summary
Electric ride-pooling services face challenges balancing passenger pickups, route planning, battery levels, and limited charging stations. The authors created a simulator and a learning system that helps decide which passengers to reassign between vehicles to reduce overall delays and costs. Their method respects constraints like battery life and waiting times and uses smart trial moves to find better routes. Testing in a realistic setting showed it saves costs and serves more passengers, even for very large fleets with few chargers.
What this means in practice
- •For ride-hailing operators: Reduce costs and increase served passengers by optimizing EV routes and charging schedules with learned repair decisions under finite charger queues.
- •For fleet management teams: Improve electric vehicle utilization by managing battery reserves and pickup constraints jointly with charging queue awareness in large-scale urban operations.
Authors
Mai Pham, Vikrant S. Vaze, Peter Chin
Abstract
Electric ride-pooling must jointly manage passenger service, routes, batteries, and finite chargers; a locally useful relocation can reduce later service. We introduce a discrete-event ride-pooling simulator with ordered passenger stops, pickup and ride-time constraints, battery reserves, charger travel, and finite first-come, first-served (FCFS) charging queues. On top of a common dispatcher, we add a learned repair layer that moves uncollected passengers between vehicles, uses a supervised score to estimate later effects, and uses a two-stage proximal-policy-optimization (PPO) policy to focus computation on promising moves. Every executed move must satisfy route, battery, and time constraints and provide an immediate route-cost improvement. For larger instances, we limit the number of candidate moves and apply several non-conflicting repairs at once. On 12 held-out Manhattan episodes with 100 requests, 30 EVs, and one plug per station, supervised repair reduces operational cost by 6.57\% versus no repair (12/12 wins) and serves 74.92 rather than 72.75 requests. Two-stage PPO stays within 1.43\% of supervised repair with 95.4\% fewer exact trials, while our experiments scale to 8,000 requests and 2,400 EVs with cost reductions across all three larger development settings. Queue-aware charging reduces waiting by 41.0\%; under a declared 1.5-kW queue-idle load, operational electricity per served request falls 1.73\%.