A Real-Time Multi-modal Framework for Human-Centric Requirements Engineering in Autonomous Vehicles
Bibliographic record
Abstract
Trustworthy and human-centric adaptation remains a central challenge for autonomous vehicles (AVs), which operate in dynamic and uncertain environments. This paper proposes a real-time, multi-modal, and self-adaptive framework that operationalizes Human-Centric Requirements Engineering (HCRE) by treating contextual signals as non-functional requirements (NFRs), where NFRs denote stakeholder-oriented soft goals such as trust, cognitive comfort, and perceived safety that must be continuously fulfilled alongside functional driving tasks. The framework integrates driver emotions, behaviors, traffic conditions, and vehicle dynamics within an interpretable neural architecture to deliver proactive behavior recommendations aligned with drivers’ needs, and unlike prior approaches that rely on static rules or thresholds, it continuously elicits, monitors, and fulfills latent human-centric goals through transparent and context-aware adaptation. Trained and evaluated on the AIDE dataset, the system achieves high accuracy across perception modules $(83-93 \%)$ and $89.32 \%$ exact match accuracy for integrated behavior recommendations, satisfies real-time constraints with an average inference latency of 106.84 ms, and maintains interpretability through explicit mappings from multimodal input to adaptive output. The results demonstrate the feasibility of embedding HCRE principles, particularly dynamic NFR fulfillment, into the core of AV control architectures, thereby enabling emotionally responsive and stakeholder-aligned autonomous systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".