The capacity of surveying and analysing personal mobility in indoor and outdoor spaces is a critical driver of the innovation towad sustainable and responsible mobility which is a challenge for the 21st century. But there is no practical, affordable, reliable, accurate and ethical technological solution for mapping pedestrian traffic. The good functioning of existing solutions is strongly limited by the availability and density of dedicated telecommunication network. Not only are they mainly working outdoors but they often force the user to choose a particular device, to adopt a specific behaviour and to share private data. Consequently there is a need for innovative geolocalisation processes.
The project smartWALK, for smart Walk with Autonomous Localisation Knowhow, aims at developing new localisation algorithms based on data recorded with units already available in daily life following an autonomous processing strategy. New systems and methods will be investigated for filtering data from a handheld smartphone and estimate pedestrian’s displacement irrespective of the surroundings. The research includes a smart processing of walking features with MEMS signals collected during naturalistic walk. Thanks to the design and production of a multi-sensors pedestrian navigation platform, a dead reckoning strategy will be followed for proposing adaptive step length estimation and walking direction computation with temporal and frequency analysis, quaternion based filtering and computational geometry. The quality of the research outcomes will be assessed with realistic data collections.
The nature of the proposed research is a safeguard for possible misuse of geolocation information, which will drastically change the strategy for addressing large public mobility issues. It will provide innovative algorithms for processing handheld signals and initiate new research ideas. The scientific results will provide a leading role to Europe in the market of personal navigation.
Appel à propositions
Voir d’autres projets de cet appel
Régime de financementMC-CIG - Support for training and career development of researcher (CIG)
77447 Marne La Vallee Cedex 2
Voir sur la carte