The Influence of Advanced Driver Assistance Systems on Fatigue Development Among Long-Haul Truck Drivers

Huang, Chunxi; Wang, Zuyuan; He, Dengbo · 2025 · Springer Series in Design and Innovation

DOI: 10.1007/978-981-95-0289-9_19

archive: archived pipeline: cataloged verified

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

Summary

This study investigates the impact of Advanced Driver Assistance Systems (ADAS) on fatigue development among long-haul truck drivers, addressing a critical gap in road safety research. While ADAS is increasingly deployed in heavy trucks to reduce driver workload, prior research in the passenger car domain suggests that automation may increase driver susceptibility to fatigue compared to manual driving. Given that driving fatigue contributes to 15% of traffic accidents in China and is a significant risk for long-haul drivers who operate for 10–14 hours daily, this research aims to determine whether ADAS mitigates or exacerbates fatigue in professional truck drivers during real-world conditions. The researchers conducted naturalistic driving experiments involving three professional long-haul truck drivers with over two years of ADAS experience. The study utilized a Jie Fang J7 heavy truck equipped with SAE Level 2 ADAS, covering an 802 km highway route between Suzhou and Xiaogan, China. Each driver completed two rounds of experiments, driving manually on one day and with ADAS assistance on another, resulting in over 120 hours of data collection. Fatigue was measured using three methods: eye-tracking metrics (blink frequency, blink duration, pupil diameter, and PERCLOS), Driving Response Task (DRT) response times triggered by auditory stimuli every two hours, and subjective sleepiness ratings using the Karolinska Sleepiness Scale (KSS) every hour. Statistical analysis employed linear mixed-effects models to account for repeated measures and individual differences. The results demonstrated that ADAS significantly reduced fatigue levels compared to manual driving. Eye-tracking data showed that drivers using ADAS exhibited higher pupil diameter, lower blink frequency, shorter blink duration, and lower PERCLOS values, all indicators of reduced fatigue. Subjective KSS scores were also significantly lower in the ADAS condition. Furthermore, DRT response times revealed a significant interaction between driving mode and time; while response times increased with driving duration in both conditions, the benefit of ADAS became more pronounced as driving time increased, indicating that automation helps maintain alertness during prolonged trips. The study concludes that ADAS effectively reduces fatigue in long-haul truck drivers, contradicting findings from passenger car studies where automation often induced passive fatigue. The authors attribute this difference to the professional drivers’ ability to self-regulate attention and the higher ecological validity of real-world driving compared to simulator-based studies. These findings suggest that ADAS can enhance safety for heavy vehicle operators by mitigating fatigue during long-distance transport. However, the authors note that the small sample size limits generalizability, recommending future research with larger participant groups to validate these results.

Key finding

Long-haul truck drivers experienced significantly lower levels of physiological and subjective fatigue when driving with ADAS assistance compared to manual driving.

Methodology

naturalistic

Sample size: 3

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.

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.

• truck driver fatigue
• drowsiness detection algorithms
• time on task
• drowsiness

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: physiological data, behavioral performance data
• Methodological Resource: tool software