We propose a software layered architecture for autonomous vehicles whose efficiency is driven by pull-based acquisition of sensor data. This multiprocess software architecture, to be embedded into the control loop of these vehicles, includes a Belief-Desire-Intention agent that can consistently assist the achievement of intentions. Since driving on roads implies huge dynamic considerations, we tackle both reactivity and context awareness considerations on the execution loop of the vehicle. While the proposed architecture gradually offers 4 levels of reactivity, from arch-reflex to the deep modification of the previously built execution plan, the observation module concurrently exploits noise filtering and introduces frequency control to allow symbolic feature extraction while both fuzzy and first order logic management are used to enforce consistency and certainty over the context information properties. The presented use-case, the daily delivery of a network of pharmacy offices by an autonomous vehicle taking into account contextual (spatio-temporal) traffic features, shows the efficiency and the modularity of the architecture, as well as the scalability of the reaction levels.
A.-C. Chaouche, J.-M. Ilié, A. Hebik and F. Pêcheux. 2023. Integration a Contextual Observation System in a Multi-Process Architecture for Autonomous Vehicles. Computing and Informatics (CAI), 42, 3 (August 2023), Institute of Informatics, SAS Dúbravská cesta 9 845 07 Bratislava Slovakia, 716-740. DOI: https://doi.org/10.31577/cai_2023_3_716.
APA :
Chaouche, A.-C., Ilié, J.-M., Hebik, A. & Pêcheux, F. (2023, August). Integration a Contextual Observation System in a Multi-Process Architecture for Autonomous Vehicles. Computing and Informatics (CAI), 42(3), Institute of Informatics, SAS Dúbravská cesta 9 845 07 Bratislava Slovakia, 716-740. DOI: https://doi.org/10.31577/cai_2023_3_716
IEEE :
A.-C. Chaouche, J.-M. Ilié, A. Hebik and F. Pêcheux, "Integration a Contextual Observation System in a Multi-Process Architecture for Autonomous Vehicles". Computing and Informatics (CAI), vol. 42, no. 3, Institute of Informatics, SAS Dúbravská cesta 9 845 07 Bratislava Slovakia, pp. 716-740, August, 2023. DOI: https://doi.org/10.31577/cai_2023_3_716.
BibTeX :
@article{misc-lab-420, author = {Chaouche, Ahmed-Chawki and Ili\'{e}, Jean-Michel and Hebik, Assem and P\^{e}cheux, Fran\ccois}, title = {Integration a Contextual Observation System in a Multi-Process Architecture for Autonomous Vehicles}, journal = {Computing and Informatics (CAI)}, volume = {42}, number = {3}, issn = {1335-9150}, pages = {716--740}, publisher = {Institute of Informatics, SAS Dúbravská cesta 9 845 07 Bratislava Slovakia}, year = {2023}, month = {August}, doi = {10.31577/cai\_2023\_3\_716}, url = {https://www.cai.sk/ojs/index.php/cai/article/view/2023\_3\_716}, keywords = {Autonomous vehicle, multi-process architecture, context-awareness, contextual planning, reactive behavioral strategies, logical context modeling} }
RIS :
TI - Integration a Contextual Observation System in a Multi-Process Architecture for Autonomous Vehicles AU - A.-C. Chaouche AU - J.-M. Ilié AU - A. Hebik AU - F. Pêcheux PY - 2023 SN - 1335-9150 JO - Computing and Informatics (CAI) VL - 42 IS - 3 SP - 716 EP - 740 PB - Institute of Informatics, SAS Dúbravská cesta 9 845 07 Bratislava Slovakia AB - We propose a software layered architecture for autonomous vehicles whose efficiency is driven by pull-based acquisition of sensor data. This multiprocess software architecture, to be embedded into the control loop of these vehicles, includes a Belief-Desire-Intention agent that can consistently assist the achievement of intentions. Since driving on roads implies huge dynamic considerations, we tackle both reactivity and context awareness considerations on the execution loop of the vehicle. While the proposed architecture gradually offers 4 levels of reactivity, from arch-reflex to the deep modification of the previously built execution plan, the observation module concurrently exploits noise filtering and introduces frequency control to allow symbolic feature extraction while both fuzzy and first order logic management are used to enforce consistency and certainty over the context information properties. The presented use-case, the daily delivery of a network of pharmacy offices by an autonomous vehicle taking into account contextual (spatio-temporal) traffic features, shows the efficiency and the modularity of the architecture, as well as the scalability of the reaction levels. KW - Autonomous vehicle KW - multi-process architecture KW - context-awareness KW - contextual planning KW - reactive behavioral strategies KW - logical context modeling DO - 10.31577/cai_2023_3_716 UR - https://www.cai.sk/ojs/index.php/cai/article/view/2023_3_716 ID - misc-lab-420 ER -