Partially automated driving has higher workload than manual driving: An on‐road comparison of three contemporary vehicles with SAE Level 2 features
DOI: 10.1002/hfm.20969
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 drivers’ perceived workload in partially automated driving (SAE Level 2) compared to manual driving in naturalistic, on-road conditions. While previous research has yielded conflicting results regarding whether automation reduces or increases workload, most studies relied on simulators or closed test tracks that fail to capture the complexity of real-world traffic. This research aims to resolve this ambiguity by examining workload across different driving environments and driver experience levels using contemporary vehicles with Level 2 features. The experimental design involved eight participants who completed 12 driving sessions each, utilizing three vehicles: a Jaguar I-PACE, a Mercedes S350, and a Tesla Model S. Participants drove in both manual and automated modes across two distinct environments: a monotonic highway and a complex urban area. Workload was measured using the NASA-Task Load Index (NASA-TLX), assessing mental, physical, and temporal demands, as well as frustration, effort, and performance. Participants were categorized into less-experienced and more-experienced groups based on their prior use of automated features. Statistical analysis employed Wilcoxon signed-rank tests to compare workload scores between conditions. The results demonstrated that perceived workload was significantly higher in partially automated driving than in manual driving across all three vehicles and both environments. This increase was driven primarily by higher mental demand and frustration scores. Workload was also substantially higher in complex urban environments compared to monotonic highway settings. Furthermore, less-experienced drivers reported higher workload levels than more-experienced drivers in automated conditions, suggesting that familiarity with automation mitigates some cognitive burden. The authors attribute the increased workload in automated mode to the continuous requirement for drivers to monitor the system, interpret its behavior, and maintain readiness to intervene, particularly when the system reaches its functional limits in complex traffic. The study concludes that current SAE Level 2 automation does not reduce driver workload in real-world scenarios; instead, it imposes additional cognitive demands due to the supervisory role required. The findings highlight that environment complexity and driver experience are critical moderating factors. The authors recommend that vehicle manufacturers improve interface design to provide clearer status information and consider multimodal alerts to support take-over requests. Additionally, they suggest that driver training could help develop better mental models of automation limitations, thereby reducing perceived workload and enhancing safety. These insights are crucial for the development of future automated systems and for understanding the human factors involved in the transition to higher levels of automation.
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | unpaywall | — | — | 2 | 2026-08-09 |
| extract | success | pdftotext | — | — | 4 | 2026-08-10 |
| clean | success | clean | — | — | 2 | 2026-08-10 |
| chunk | success | chunk | — | — | 2 | 2026-08-10 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 2 | 2026-08-10 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 17 | 2026-08-11 |
| verify | partial | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- mental demand
- hands on hands off engagement
- situational awareness
- driverless ads
- automation
- stress driving
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
- Theoretical Contribution: theory or model, conceptual framework