Surface Electromyography-Controlled Pedestrian Collision Avoidance: A Driving Simulator Study
DOI: 10.1109/jsen.2021.3070597
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 addresses the challenge of pedestrian collision avoidance for drivers with unilateral upper limb disabilities, such as hemiplegia or amputation, who are restricted to one-handed steering. While steering is often more effective than braking for avoiding pedestrians at short time-to-collision intervals, existing collision avoidance systems rarely accommodate drivers with upper limb impairments. The authors developed and validated a surface electromyography (sEMG)-controlled steering assistance system using the Myo armband interface. The primary objective was to determine if this sEMG-based interface could maintain vehicle stability comparable to or superior to conventional manual steering and manual takeover from automated driving during emergency evasion maneuvers. The research utilized a driving simulator experiment involving 12 healthy male test subjects, selected to approximate the demographic most prone to pedestrian collisions. Participants performed seven experimental conditions using three steering interfaces: conventional steering wheel, the Myo armband, and manual takeover from SAE Level 3 automation. Scenarios involved a pedestrian crossing the road at a time-to-collision of 0.3 seconds, with the vehicle maintained at 30 km/h via cruise control to isolate steering performance. The sEMG system translated wrist extension signals into steering commands via a proportional-integral, proportional-derivative controller. Vehicle stability was assessed primarily through the absolute average vehicle slip angle, with secondary metrics including lateral acceleration, minimum distance to the pedestrian, maximum steering wheel angle, and response time. Statistical analyses, including Wilcoxon signed-rank tests and t-tests, were employed to compare interface performance. The results demonstrated that the Myo armband interface was significantly superior to manual takeover from automated driving in terms of vehicle stability, as evidenced by lower average absolute vehicle slip angles. The sEMG interface was also comparable to conventional manual steering wheel operation. Although the Myo armband resulted in a shorter minimum distance to the pedestrian (1.62 m at crosswalks vs. 2.73 m for manual steering), it achieved this with significantly lower maximum steering wheel angles and reduced peak lateral acceleration. These dynamics contributed to more gradual vehicle trajectories and higher overall stability compared to the abrupt maneuvers associated with manual takeover and conventional steering. The study concludes that the sEMG-controlled steering assistance system is a feasible and safe alternative for drivers with upper limb disabilities. By prioritizing vehicle stability over maximum lateral displacement, the system offers a viable solution for emergency collision avoidance. The findings suggest that sEMG interfaces can effectively support driver-initiated evasion assistance, potentially expanding driving independence for individuals with hemiplegia or amputation. Future work is recommended to include participants with actual disabilities and to test the system in additional dynamic scenarios, such as avoiding other vehicles or incorporating braking mechanisms.
Key finding
The sEMG-controlled steering interface demonstrated significantly superior vehicle stability compared to manual takeover from automated driving and comparable stability to conventional steering wheel operation during pedestrian collision avoidance maneuvers.
Methodology
simulator
Sample size: 12
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 author_sweep_intake on 2026-05-08 (7 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-08 |
| archive | success | canonical_url | — | — | 7 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | openalex | — | — | 7 | 2026-05-27 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
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.