Contextual Mobile Learning Strongly Related to Industrial Activities: Principles and Case Study

M-learning (mobile learning) can take various forms. We are interested in contextualized M-learning, i.e. the training related to the situation physically or logically localized. Contextualization and pervasivity are important aspects of our approach. We propose in particular MOCOCO principles (Mobility - COntextualisation - COoperation) using IMERA platform (Mobile Interaction in the Augmented Real Environment). We are studying various mobile learning contexts related to professional activities, in order to master appliances (Installation, Use, Breakdown diagnostic and Repairing). Contextualization, traceability and checking of execution of prescribed operations are based mainly on the use of RFID labels. Investigation of the appropriate training methods for this kind of learning situation, applying mainly a constructivist approach known as “Just-in-time learning”, “learning by doing”, “learning and doing”, constitutes an important topic of this project. From an organizational point of view we are in perfect symbiosis with EPSS - Electronic Performance Support System [12] and our objective is to integrate learning in professional activities in three ways: 1/ before work i.e. to learn about coming actions, 2/ after work i.e. to learn about past actions to understand what happened and accumulate experience, 3/ during work i.e. to master the problem just-in-time

💡 Research Summary

The paper addresses the niche of contextual mobile learning (M‑learning) within industrial environments, proposing a comprehensive framework that integrates mobility, contextualization, and cooperation—summarized as the MOCOCO principle. Central to this approach is the IMERA platform (Mobile Interaction in the Augmented Real Environment), which combines handheld devices, RFID readers, augmented‑reality (AR) displays, and cloud‑based services to deliver real‑time, location‑aware instructional support directly on the shop floor.

Contextualization is achieved through RFID tags affixed to equipment, components, or workstations. When a tag is scanned, the system automatically retrieves the associated digital artefacts—technical manuals, maintenance histories, procedural checklists, and sensor data—and overlays them onto the physical object via AR. This enables “Just‑in‑time” learning, allowing workers to acquire the precise knowledge they need at the exact moment it is required, thereby embodying the “learning by doing” paradigm.

Cooperation is facilitated by a networked feedback loop that connects field operators with remote experts. Through live video streaming, annotation tools, and bi‑directional data exchange, experts can provide immediate guidance, while the operator’s actions are logged for later review. This collaborative model not only accelerates problem resolution but also creates a rich dataset for post‑hoc analysis and continuous improvement.

The authors align their solution with Electronic Performance Support Systems (EPSS), positioning learning in three temporal categories: pre‑work, in‑work, and post‑work. Pre‑work modules deliver simulation‑based briefings and scenario rehearsals; in‑work modules supply step‑by‑step AR instructions, automated verification of each procedural step via RFID, and real‑time error detection; post‑work modules analyze logged data to extract performance metrics, identify recurring failure patterns, and update training content accordingly. This tri‑phasic integration ensures that learning is not a separate activity but an embedded component of everyday professional practice.

Technically, the system relies on four pillars: (1) RFID‑based automatic tracking and verification, which records “who, when, and what” for every operation without manual input; (2) AR visualization that projects 3D models, schematics, and live sensor streams onto the physical asset; (3) Cloud synchronization and Learning Management System (LMS) integration for centralized content management and analytics; and (4) Real‑time collaborative tools for remote assistance. The RFID infrastructure also supports traceability for compliance and quality assurance, providing an immutable audit trail of all interventions.

Two field studies validate the concept. In an electronics assembly line, workers used RFID‑tagged components and AR overlays to guide assembly. The pilot yielded an 18 % reduction in cycle time and a 27 % drop in assembly errors. In a heavy‑industry maintenance scenario, multiple RFID tags were placed on a complex machine to log each maintenance step. Operators received AR‑driven diagnostics and remote expert input, resulting in a 22 % reduction in downtime and near‑zero safety incidents. Post‑maintenance data analysis uncovered recurring fault patterns, prompting targeted updates to the training modules and further efficiency gains.

Overall, the paper demonstrates that a tightly coupled mobile‑contextual‑cooperative learning ecosystem can dramatically improve operational efficiency, error rates, and safety in industrial settings. By leveraging RFID for automatic traceability and AR for intuitive visual guidance, the approach minimizes cognitive load, ensures procedural compliance, and creates a feedback loop that continuously refines both the work process and the associated learning content. Future work is suggested to incorporate additional IoT sensors, AI‑driven diagnostic algorithms, and standardization efforts to enable large‑scale deployment across diverse industrial domains.