Multi-modal and multi-sensor zero-distraction interaction interface for two wheel vehicles on the move

Preparatory Action on the enhancement of European industrial potential in the field of Security research

Concept and objectives

MoveON investigated the application of multi-modal and multi-sensor zero-distraction interfaces for enabling 2-wheel vehicle drivers to access online, in real-time and taking into account on the road safety issues, services and information resources. MoveON also supported the complimentary use of speech and tactile modalities pushing beyond the state-of-the-art for motorcycle set-ups. The intended project target users were the police force motorcyclists and motorcycle riders in all walks of life.

A scientific objective of profound significance addressed the development of a robust speech-processing module, which will be complemented with a dialogue system incorporating speech recognition and a text-to-speech component. Technological objectives involved the integration of appropriate low cost, efficient, realistic systems. Technological objectives were further sought in the employment of multiple sensors attached to the motorcycle to provide information that was fused with the user's input taking into account the level of the user's driving risk. Information channelling was developed deciding on the amount, time and form of the information that was delivered to the user.

MoveON deployed the Usability Relationship Evaluation Methodology on controlled field-experiments for assessing the user's distraction while interacting with the prototype system. The project developed evaluation scenarios that energised situations in which to validate the motorcyclists' driving attention disruption while interacting with the MoveON multimodal interface. The final system was evaluated in specific command and control situated contexts of actors, legacy systems and domain constraints.

The success of this project relied on the following major achievements:
· Creation of small to medium-scale spoken language resources for developing on-   motorcycle voice driven information services and command and control systems in   English.
· Creation of a noise database covering the different driving conditions.
· Robust automatic speech recognition under different driving conditions.
· Modular support for multiple modalities through a multi-modal and multi-sensor   framework architecture.
· Design of a low cost communications enabled helmet encompassing state of the art   noise reduction features compliant with helmet manufacturing safety standards and   prototype development.