UMR CNRS 7253
PRETIV Project
PRETIV Project
PRETIV Project
PRETIV Project
PRETIV Project
PRETIV Project


Safety and driving assistant systems for a vehicle require advanced technologies in terms of perception and understanding of its external environment. PRETIV is decomposed into 1 + 3 tasks:

  • Task 0: Coordination, management, dissemination + an Advisory Board with a car manufacturer;    
  • Task 1: Multimodal perception;
  • Task 2: Reasoning and scene understanding;
  • Task 3: Test bed integration, experiment design and comparative studies.


Objectives, expected results and innovative nature of PRETIV are summarized as follows: 

  • Development of an online multimodal perception system which incorporates vehicle localization, mapping of static objects of its environment, detecting and tracking moving objects in probabilistic frameworks through multimodal sensing data and knowledge fusion;
  • Development of offline reasoning methods based on sensed data, in order to learn semantics, activity and interaction patterns (vehicle – other objects, vehicle – infrastructure), which could be injected as the contextual and country-specific a priori information to make the online perception more general for international use. This analysis aims at comparing perception methods in different traffic environments, and aims at identifying better context-specific a priori information leading to more effective perception algorithms. It includes traffic situation awareness, i.e. generation of indicators to help decision, to estimate the dangerousness of the driving situation by considering factors of sensing uncertainty and infrastructure;
  • Cross-experiments and comparative studies are to be conducted in real transnational traffic situations (France and China) by implementing the jointly developed core algorithms on two different test-bed vehicles of the partners, which will permit cross-fertilization of sensing techniques between the three research groups;
  • A comparative dataset containing the experimental data, labeled training sets in typical traffic scenarios in both France and China with ground-truth, which will be used in learning country-specific traffic semantics, and will be opened to public to promote comparative researches on transnational traffic semantics and behaviors. To our knowledge, no such dataset has been proposed for international use.


Towards better perception models and identify needs for specific parametrization for a transnational use.

The research proposal is based on the solid experience of three laboratories in France (CNRS and INRIA) and China (Peking University), and is voluntarily oriented towards cross-fertilization of methods and knowledge. For this purpose, considering their respective knowledge and experience, the partners will put emphasis on sharing methods such as learning under partial supervision, and data fusion including probabilistic and belief function based frameworks for handling incompleteness and uncertainties in the models and the measures. An Advisory board is made up of a car manufacturer present both in France and in china. It will bring in the point of view, constraints and advices from a car manufacturer.

 




· Last modified: 03/09/2012 06:15 by fdavoine