Abstract

The Indiana Department of Transportation (INDOT) spends approximately $19 million annually on roadside mowing, which is a process that is time-consuming, costly, and poses safety risks. Automated mowing solutions have the potential to reduce costs and increase safety, but they will need to be extremely well tested before being deployed. In this work, data from current mowing practices was collected using machine mounted cameras, which was used to inform the creation of a digital twin environment that allows for rigorous initial testing of potential autonomous solution with no risk. The digital twin was created using digital elevation models of Indiana highway corridors and geolocated features to create a high-fidelity test environment. Algorithms including path planning, obstacle avoidance, and road entry detection were created and tested in a simulation and validated in a real-world environment. Results showed that the digital twin was able to simulate real-world conditions and accurately demonstrate how the algorithms performed.

Keywords

mowing, automation, digital twin, simulation

Report Number

FHWA/IN/JTRP-2025/01

SPR Number

4702

Performing Organization

Joint Transportation Research Program

Publisher Place

West Lafayette, Indiana

Date of Version

2025

DOI

10.5703/1288284317840

Share

COinS