ParkSense: Where Should a Delivery Driver Park? Leveraging Idle AV Compute and Vision-Language Models
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors designed ParkSense, a system that helps autonomous vehicles find legal parking spots close to store entrances during food delivery. It uses moments when the vehicle is stopped, like waiting at red lights or in traffic, to analyze satellite and street images with a vision-language model. This lets the car pick precise parking spots, potentially saving drivers a lot of time and increasing their earnings. The authors also introduce a new problem called Delivery-Aware Precision Parking and highlight future research possibilities in this area.
Autonomous vehiclesVision-language modelsSatellite imageryStreet view imageryLast-mile logisticsPrecision parkingDelivery optimizationInference timeQuantized models
Authors
Die Hu, Henan Li
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.