A Cognitive Advanced Driver Assistance Systems Architecture for Autonomous-Capable Electrified Vehicles
- 17 September 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 5 (1) , 48-58
Abstract
Autonomous Vehicle industry is making rapid progress in the development of commercial vehicles with higher levels of autonomy. Although, the general Advanced Driver Assistance System architecture is widely discussed, limited details are available about the functionality of the modules and their interactions, backed up by scientific justification. This, in turn, limits the utilization of such an architecture for pragmatic implementation. A Cognitive ADAS architecture for level 4 autonomous-capable electrified vehicles is proposed. Variations for levels 3 and 3.5, which is simply seen to be a combination of 3 and 4, with the primary fallback through a human driver and the secondary through an Automated Driving System, are also presented. A simulation framework is built for highway driving based on the proposed level 4 architecture for an enhanced Tesla Model S. It was concluded that the autonomous control provided a 23% energy economy increase, on average, compared to a human driver control. Through a detailed sensitivity analysis, the optimal mission/motion planning and energy management in addition to the positive impact on the electrified vehicle battery, motor, and acceleration/deceleration profiles are considered to contribute to this significant increase in the energy economy of an autonomous-controlled electrified vehicle.Keywords
Funding Information
- Canada Excellence Research Chairs, Government of Canada
This publication has 19 references indexed in Scilit:
- Impact of Connectivity and Automation on Vehicle Energy UseSAE International Journal of Advances and Current Practices in Mobility, 2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Prediction of Vehicle Velocity for Model Predictive ControlIFAC-PapersOnLine, 2015
- Autonomous Cars: Past, Present and Future - A Review of the Developments in the Last Century, the Present Scenario and the Expected Future of Autonomous Vehicle Technology2015
- Three Decades of Driver Assistance Systems: Review and Future PerspectivesIEEE Intelligent Transportation Systems Magazine, 2014
- Transferability of driver speed and lateral deviation measurable performance from semi-dynamic driving simulator to real traffic conditionsEuropean Transport Research Review, 2013
- Junior: The Stanford entry in the Urban ChallengeJournal of Field Robotics, 2008
- Stanley: The robot that won the DARPA Grand ChallengeJournal of Field Robotics, 2006
- "How Long Does It Take to Stop?" Methodological Analysis of Driver Perception-Brake TimesTransportation Human Factors, 2000
- The Autonomous Land Vehicle (ALV) Preliminary Road-Following Demonstration1985