ParkSense: Where Should a Delivery Driver Park? Leveraging Idle AV Compute and Vision-Language Models
This addresses parking inefficiencies for food delivery drivers, though it is incremental as it applies existing methods to a new domain.
The paper tackles the problem of precise parking-spot selection for delivery drivers by proposing ParkSense, a framework that uses idle autonomous vehicle compute and vision-language models on pre-cached imagery to identify entrances and legal parking zones, estimating annual per-driver income gains of 3,000-8,000 USD in the U.S.
Finding parking consumes a disproportionate share of food delivery time, yet no system addresses precise parking-spot selection relative to merchant entrances. We propose ParkSense, a framework that repurposes idle compute during low-risk AV states -- queuing at red lights, traffic congestion, parking-lot crawl -- to run a Vision-Language Model (VLM) on pre-cached satellite and street view imagery, identifying entrances and legal parking zones. We formalize the Delivery-Aware Precision Parking (DAPP) problem, show that a quantized 7B VLM completes inference in 4-8 seconds on HW4-class hardware, and estimate annual per-driver income gains of 3,000-8,000 USD in the U.S. Five open research directions are identified at this unexplored intersection of autonomous driving, computer vision, and last-mile logistics.