Artificial Co-Drivers as a Universal Enabling Technology for Future Intelligent Vehicles and Transportation Systems
DOI: 10.1109/tits.2014.2330199
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This position paper introduces the concept of "artificial co-drivers" as a universal enabling technology for future intelligent transportation systems. The authors address the limitation of current driver assistance systems, which often rely on rigid "sense–think–act" architectures that struggle with scalability and meaningful human-machine interaction. Motivated by the need for smart collaboration between humans and vehicles, the paper proposes an artificial agent capable not only of driving like a human but also of inferring human intentions and correcting mistakes, thereby acting as a peer rather than a mere tool. The methodology is grounded in cognitive science theories, specifically the emulation theory of cognition and the Shared Circuit Model. The authors argue that effective co-driving requires an architecture based on embodied cognition, where agents use internal forward emulators to simulate sensory inputs and inverse models to generate optimal motor primitives. These primitives are derived using Optimal Control (OC) principles that mimic human movement efficiency, such as the minimum variance principle and the two-thirds power law. The paper details the implementation of this concept within the EU project interactIVe, specifically through a Centro Ricerche Fiat (CRF) demonstrator. The system utilizes a subsumptive hierarchy of perception-action loops, integrating longitudinal and lateral motor primitives (e.g., speed matching, lane alignment) to create human-like reference maneuvers. The study presents the architectural design and theoretical validation of this co-driver, demonstrating how it conforms to guidelines for human-like sensory-motor strategies. The CRF implementation employs a "Continuous Support" function that monitors driving and intervenes when necessary, using the co-driver metaphor to integrate various assistance forms. The authors show that by using forward emulators to test hypotheses about human intentions against observed behaviors, the system can achieve intention recognition and cooperative control. While the paper focuses on the design and theoretical framework rather than extensive empirical performance metrics, it clarifies the limitations of the current implementation, such as the reliance on quasi-static vehicle models and simplified obstacle motion predictions. The significance of this work lies in establishing a technological roadmap for smart collaborative control in intelligent vehicles. By framing the co-driver as a universal enabling technology, the authors argue that this approach bridges the gap between fully autonomous vehicles and traditional driver assistance systems. It offers a scalable architecture that supports both preventive safety and cooperative systems, setting out a program for future research into learning by simulation and more complex human-machine interactions. This framework provides a foundation for developing vehicles that can naturally interact with human drivers, enhancing safety and efficiency through empathic, intention-aware collaboration.
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 | OpenAlex-citations | — | — | 1 | 2026-06-25 |
| archive | success | unpaywall | — | — | 2 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-25 |
| chunk | success | chunk | — | — | 1 | 2026-06-25 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-25 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-25 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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).
- Methodological Resource: tool software
- Theoretical Contribution: computational model, conceptual framework