ParkSense: Where Should a Delivery Driver Park? Leveraging Idle AV Compute and Vision-Language Models

TL;DR

ParkSense is a system that uses idle autonomous vehicle compute to identify optimal parking spots near merchant entrances, reducing delivery times and increasing driver income.

Contribution

It introduces the DAPP problem, leveraging vision-language models on satellite and street view images for precise parking spot selection.

Findings

A 7B VLM completes inference in 4-8 seconds on HW4 hardware.

Estimated annual income gains per driver are $3,000-$8,000 in the U.S.

ParkSense effectively identifies legal parking zones and entrances.

Abstract

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.