AI 中文总结
针对电动拼车中有限充电队列问题，提出带学习修复层的调度框架，通过监督评分和两阶段PPO策略优化车辆间乘客移动，在曼哈顿实验中降低运营成本6.57%并提升服务量。
AI 中文摘要
电动拼车必须联合管理乘客服务、路线、电池和有限充电器；一个局部有用的重新定位可能会降低后续服务。我们引入了一个具有有序乘客站点、接送和乘车时间约束、电池储备、充电器行程以及有限先到先服务（FCFS）充电队列的离散事件拼车模拟器。在通用调度器之上，我们增加了一个学习修复层，该层在车辆之间移动未收集的乘客，使用监督评分来估计后续影响，并使用两阶段近端策略优化（PPO）策略将计算集中在有希望的移动上。每个执行的移动必须满足路线、电池和时间约束，并提供即时的路线成本改进。对于较大的实例，我们限制候选移动的数量，并同时应用多个不冲突的修复。在12个保留的曼哈顿情节中，有100个请求、30辆电动汽车和每个站点一个插头，监督修复将运营成本降低了6.57%（12/12胜出），并服务了74.92个请求，而不是72.75个。两阶段PPO保持在监督修复的1.43%以内，精确试验减少了95.4%，而我们的实验扩展到8,000个请求和2,400辆电动汽车，在所有三个更大的开发设置中均降低了成本。队列感知充电将等待时间减少了41.0%；在声明的1.5千瓦队列空闲负载下，每个服务请求的运营电力下降了1.73%。
英文摘要
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\%.
