A Case Study in Urban Mobility
Open Access DepositedOptimizing Robotaxi Deployment Through Behavior-Based Demand Clustering
The growing integration of autonomous vehicles (AVs) into urban transportation systems has introduced new challenges in fleet management and operational planning. Traditional vehicle staging strategies, often based on static geography or fixed heuristics, fail to reflect behavioral patterns in rider demand. As a result, deployments are frequently inefficient and exhibit service imbalances. This Praxis proposes a data-driven framework that leverages behavioral demand clustering to inform robotaxi hub deployment strategies. Using publicly available ride-hailing data from Boston, the study applies K-Means clustering to four ride-level operational metrics
average ride distance, price per mile, surge multiplier, and ride volume. These clusters are consolidated into operational hubs, each representing a functionally distinct service area. Exploratory analysis of spatial and temporal trends provides actionable insights for vehicle staging, shift planning, and pricing logic. The findings demonstrate that behaviorally segmented zones offer a more adaptive and efficient structure for AV fleet operations than static or proximity-based methods. The resulting framework supports equitable service distribution, scalable deployment, and operational alignment with real-world demand. It provides a replicable foundation for autonomous mobility planning in high-density urban environments.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.