Evaluating the Human-Automated Maintenance Vehicle Interaction for Improved Safety and Facilitating Long-Term Trust

Miller, Erika E.; Pourfalatoun, Shiva · 2021 · ROSA P / Colorado. Dept. of Transportation. Applied Research and Innovation Branch

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This study evaluates Department of Transportation (DOT) workers’ perceptions of Automated Truck-Mounted Attenuators (ATMAs) to determine how user acceptance, training, and operational interactions influence safety and trust. ATMAs remove human drivers from vehicles positioned in high-risk work zones, aiming to reduce injury potential from errant vehicle strikes. The research was motivated by the need to validate safety improvements and identify barriers to safe adoption, as improper operation of automated systems can undermine project success. The specific objectives were to understand worker acceptance of ATMA technology, identify successful and improvable human-vehicle interactions, and assess how varying training regimens impact perceptions and usage. The researchers conducted a survey of 13 DOT workers with experience using ATMAs from Colorado and California. Due to limited deployment, the sample size was small but comprised individuals with actual on-road or training experience. Participants were categorized into "High Experience" (N=7) and "Low Experience" (N=6) groups based on the diversity of their training. High Experience workers received training in classroom, test track, and parking area settings, averaging over two years of ATMA experience. Low Experience workers received less diverse training, averaging under one year of experience. Data were analyzed using Excel and R to compare perceptions across groups regarding vehicle design, safety, trust, and operating limitations. Results indicated that workers generally held positive views of ATMA technology, citing improved safety, reliability, and reasonable workload. Participants agreed that ATMAs would reduce crash severity and were an improvement over human-driven attenuators, though they did not believe the technology would reduce crash frequency or project duration. Confidence in the automation’s ability to operate in complex environments—such as adverse weather, poor visibility, or dense traffic—was low. High Experience workers reported significantly higher confidence in their ability to override the automation in critical situations and possessed a better understanding of operating limits, including higher perceived safe operating speeds. They also rated their training as more effective, particularly for hands-on skills like starting and overriding the system. Both groups emphasized the importance of structured operating procedures, such as checklists and maintaining visual line of sight. The study concludes that investments in ATMAs are likely to be accepted and adopted by workers, provided that training is comprehensive. Diverse training involving classroom instruction and hands-on practice in test tracks and parking areas significantly improves worker confidence, trust, and understanding of system capabilities. While ATMAs are suitable for non-complex driving environments, increased worker exposure and continued training are necessary to build comfort in complex roadway conditions. The findings suggest that the safety benefits of reduced crash severity outweigh potential increases in project duration, and that proper training is essential for achieving the intended safety improvements in work zones.

Key finding

Workers with more diverse training in classroom and hands-on settings demonstrated significantly higher trust in the ATMA technology and greater confidence in their operational abilities compared to those with limited training.

Methodology

survey

Sample size: 13

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• trust calibration
• automation
• automation surprise
• acceptance adoption
• trust in automation foundations
• automation complacency bias

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: self report data