Incentive Systems for New Mobility Services

With rapid population growth and urban development, traffic congestion has become an inescapable issue in large metropolitan regions. Research studies have proposed different strategies to control traffic, ranging from roadway expansion to transportation demand management programs. Among these strategies, congestion pricing and incentive offering schemes have been widely studied as reinforcements for traffic control in traditional traffic networks where each driver is a “player” in the network. In such a network, the “selfish” behavior of individual drivers prevents the entire network to reach a socially optimal operation point. In future mobility services, on the other hand, a large portion of drivers/vehicles may be controlled by a small number of companies/organizations. In such a system, offering incentives to organizations can potentially be much more effective in reducing traffic congestion rather than offering incentives directly to drivers. This research project studies the problem of offering incentives to organizations to change the behavior of their individual drivers (or individuals using their organization’s services). The incentives are offered to each organization based on their aggregated travel time loss across all their drivers. This step requires solving a large-scale optimization problem to minimize the system-level travel time. We propose an efficient algorithm for solving this optimization problem. To evaluate the performance of the proposed algorithm, multiple experiments are conducted by Los Angeles traffic data. Our experiments show that the proposed algorithm can decrease the system-level travel time by up to 6.9%. Moreover, our experiments demonstrates that incentivizing organizations can be up to 8 times more efficient than incentivizing individual drivers in terms of incentivization monetary cost.

随着人口快速增长与城市发展进程加速，交通拥堵已成为大都市地区难以规避的共性难题。过往研究已提出多种交通管控策略，涵盖从道路扩容到交通需求管理项目的多元范畴。在此类策略中，拥堵定价与激励机制作为传统交通网络的管控补强手段得到了广泛研究——在这类网络中，每位驾驶员均为网络中的参与者（player）。在此类网络环境下，个体驾驶员的“利己”行为会阻碍整个交通网络达成社会最优运行状态。而在未来出行服务场景中，大量驾驶员与车辆可能受少数企业或机构统筹管控。在此类系统中，向机构发放激励相比直接针对驾驶员提供激励，在缓解交通拥堵方面往往具备更显著的效果。本研究聚焦向机构提供激励以引导其旗下个体驾驶员（或使用其机构服务的出行个体）调整出行行为的相关问题。激励额度将根据各机构旗下所有驾驶员的总出行时间损失进行核算与发放，该环节需求解大规模优化问题以最小化系统层面的总出行时间。为此，我们提出一种可高效求解该优化问题的算法。为验证所提算法的性能，本研究采用洛杉矶市交通数据集开展多组对比实验。实验结果表明，所提算法可将系统总出行时间最高降低6.9%。此外，实验还证实，从激励资金成本维度来看，对机构实施激励的效率最高可达直接激励个体驾驶员的8倍。