A major uncertainty in the diffusion of autonomous vehicles is the split between ownership and automated mobility services. We calculate total cost of ownership and use (TCOU) to compare four alternatives: private manually driven vehicles, private automated vehicles, automated on-demand exclusive use mobility services (ridesourcing) and automated on-demand pooled mobility services (ridesplitting), for both conventional and electric propulsions. We also included potential usefulness of travel time in the driverless vehicles in the TCOU calculations, thus including some of the non-financial factors in travel decision making. While nearly all current studies are limited to comparing average representative trips or mileage of existing vehicles, we calculate TCOUs for every vehicle in the UK National Travel Survey dataset, considering heterogeneity in mileage patterns, trip purposes, time spent driving, value of time, vehicle age, depreciation and other factors between different vehicles. The results suggest that a near-total transition to automated ride services is highly unlikely, since ownership of (automated or manually driven) vehicles continues to be the least-cost option in most cases. Even in the most pro-mobility service test case, ownership remains more cost-effective for one third of the current vehicle fleet. Regression analysis shows that higher income of the main driver, business use of the vehicle, rural location of the household or being the main household vehicle leads to a higher likelihood that automated vehicle ownership will be lower cost compared to automated mobility services. Within automated on-demand ride services, exclusive use services are cost effective for more cases compared to pooled, shared-use type options, with uncertain consequences for future travel demand.

自动驾驶汽车普及的一个主要不确定因素是所有权和自动移动服务之间的分裂。我们计算总拥有和使用成本 (TCOU) 以比较四种替代方案：私人手动驾驶车辆、私人自动驾驶车辆、自动按需专用移动服务（ridesourcing）和自动按需共享移动服务（ridesplitting），两者均适用常规和电力推进。我们还在 TCOU 计算中包括了无人驾驶车辆中旅行时间的潜在用途，从而在旅行决策中包括了一些非财务因素。虽然目前几乎所有的研究都仅限于比较现有车辆的平均代表性行程或里程，但我们计算了英国国家旅行调查数据集中每辆车的 TCOU，考虑不同车辆之间的里程模式、出行目的、驾驶时间、时间价值、车龄、折旧和其他因素的异质性。结果表明，几乎不可能完全过渡到自动乘车服务，因为在大多数情况下，拥有（自动或手动驾驶）车辆仍然是成本最低的选择。即使在最有利于移动服务的测试案例中，对于目前三分之一的车队来说，拥有所有权仍然更具成本效益。回归分析表明，与自动出行服务相比，主要驾驶员的收入、车辆的商业用途、家庭的农村位置或作为主要的家庭车辆导致自动车辆拥有成本更低的可能性更高。在自动按需乘车服务中，