The digital age has facilitated the sharing of underutilized assets. This paper focuses on privately owned autonomous vehicles (AVs), a unique class of robots that can move independently and provide transportation services. When not in personal use, private AV owners can lease their vehicles to a platform that operates an on-demand mobility service (MoD). We refer to this service as AV crowdsourcing, and develop a time-expanded network flow model that captures temporal and spatial heterogeneity in AV usage of both owners and passengers while preserving analytical tractability. We analyze the conditions under which AV crowdsourcing reduces MoD operating costs and identify their key factors, namely, the complementarity of the mobility pattern between AV owners and MoD passengers, the slack time reserved by vehicle owners, and the vehicle repositioning distance. A case study of Chicago further reveals substantial spatiotemporal heterogeneity in optimal prices and service quality. The results demonstrate how centralized dispatching can simultaneously fulfill the high demand in downtown areas while maintaining relatively high service quality in peripheral regions. Our findings provide insights into how supply heterogeneity and market conditions jointly shape the performance of AV crowdsourcing systems that leverage the underutilized private robotic assets.
🌊
