Triboelectric sensor gloves for real-time behavior identification and takeover time adjustment in conditionally automated vehicles
DOI: 10.1038/s41467-025-56169-2
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 critical safety challenge of takeover time budget (TOTB) setting in conditionally automated (Level 3) vehicles. Current systems utilize a fixed TOTB, which fails to account for the driver’s specific non-driving behaviors, leading to either redundant warning times or insufficient reaction windows that compromise safety. To resolve this, the authors propose an Intelligent Takeover Assistance System (ITAS) that dynamically adjusts the TOTB based on real-time identification of the driver’s non-driving activities. The system comprises all-round sensing gloves (AS-Gloves) equipped with triboelectric sensors, a deep learning-based behavior identification module, and a TOTB determination module. The AS-Gloves utilize flexible triboelectric nanogenerators (F-TENGs) fabricated from silicone doped with barium titanate nanoparticles and branching silver fibers. These sensors are strategically placed on the knuckles, fingertips, and palm to capture delicate hand movements and interactions with objects. The F-TENGs demonstrate high sensitivity, low power consumption, and a rapid response time of 27.4 ms. Data collection involved 40 participants performing six distinct non-driving behaviors—using a phone, smoking, drinking, interacting with the console, holding the steering wheel, and no operation—in both simulated and real driving environments. The electrical signals generated by the gloves were processed through a low-pass filter, normalized, and converted into image data to preserve spatial and temporal correlations. For behavior identification, the authors developed a time-distributed CNN-LSTM (TCNN-LSTM) model. This deep learning approach extracts complex features from the sensor data, overcoming the limitations of traditional manual feature extraction. The model achieved an identification accuracy of 94.72% across the six behaviors. Additionally, the study employed Recursive Feature Addition to optimize the sensor configuration, ensuring the system remains efficient and accurate. The ITAS then matches the identified behavior with its corresponding minimum required TOTB, allowing the vehicle to issue takeover requests with precise timing tailored to the driver’s current state. The significance of this work lies in its potential to enhance the safety and implementation of Level 3 autonomous driving systems. By replacing static, one-size-fits-all takeover budgets with a dynamic, behavior-aware system, the ITAS reduces the risk of accidents caused by delayed driver response. The integration of low-cost, self-powered triboelectric sensors with advanced deep learning algorithms provides a scalable and non-intrusive solution for monitoring driver engagement, marking a substantial step forward in human-machine interaction for automated vehicles.
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 | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 3 | 2026-08-10 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| enrich | success | semantic_scholar | — | — | 1 | 2026-08-09 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 10 | 2026-08-11 |
| verify | success | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
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: behavioral performance data
- Methodological Resource: measurement protocol
- Theoretical Contribution: conceptual framework