Work

AI-Driven Feedback Systems Reduce Sidewalk Riding on Shared E-Scooters

Year: 2024

Type: article

Abstract: This study examines the impact of AI-based feedback and speed restrictions on reducing sidewalk riding in shared e-scooters. In partnership with Spin, 100 scooters in Santa Monica, California were fitted with computer vision, with feedback features activated on half. Data from 488 trips revealed that feedback-equipped scooters spent 22% less time and 20% less distance on sidewalks. Nearly half of riders used sidewalks for less than 10% of their trip, while around 10% spent over 60% of trip time on sidewalks, regardless of feedback. These results suggest AI feedback modifies behavior but doesn’t fundamentally change diverse riding patterns.

Source: Findings

DOI: 10.32866/001c.125892

Authors: Mohammad Mehdi Oshanreh, Daniel Malarkey, Don MacKenzie

Institution: University of Washington

Language: English

Topic: Urban Transport and Accessibility

Subfield: Transportation

Field: Social Sciences

Domain: Social Sciences

SDG: Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $100