According to the European Automobile Manufacturers Association, there were over 54 Million commercial vehicles in use in Europe in 2015, and this number is growing every year. Commercial vehicles are equipped with devices emitting information regarding their location and operational status, such as speed and fuel level. Additionally, these data streams may be enriched with external data sources, such as weather information and proximity to points of interest (POIs). We have been developing CER technology to recognise various types of vehicle activity, such as dangerous driving and refuel opportunities, with the aim of optimising fleet management.
Run-Time Event Calculus (RTEC)
Our recognition engine is based on the ‘Event Calculus for Run-Time Reasoning’ (RTEC), an open-source logic programming implementation of the Event Calculus, with optimisations for continuous narrative assimilation on data streams.The video below (best viewed in full-screen mode) displays the recognition of opportunities for refuelling. A simplified version of the rules expressing such opportunities is displayed at the top left corner. When the initiation condition is satisfied it becomes green, while when the termination condition is satisfied it becomes red.
Tsilionis E., Koutroumanis N., Nikitopoulos P., Doulkeridis C. and Artikis A., Online Event Recognition from Moving Vehicles.
In Theory and Practice of Logic Programming (TPLP), 19(5-6), pp. 841–856, 2019. PDF Slides BibTeX DOI
Tsilionis E., Artikis A. and Paliouras G., Incremental Event Calculus for Run-Time Reasoning.
In 13th International Conference on Distributed and Event-Based Systems (DEBS), pp. 79–90, 2019. PDF Slides BibTeX DOI
Artikis A., Sergot M. and Paliouras G., An Event Calculus for Event Recognition.
In IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(4), 895–908, 2015. PDF BibTeX DOI