A Multi-domain Co-simulation Ecosystem for Fully Virtual Rapid ADAS Prototyping

In the last decades, vehicular control applications evolved to comprehensive Advanced Driver Assistance Systems (ADAS) with exploding complexity. Several simulation-driven approaches can ease their development, e.g., model-based design and driving simulators, which are often limited to functional traits. To bridge this gap, virtual platforms can be used for accurately simulating the entire hardware/software layer, while validating beyond-functional properties (e.g., task execution times). Moreover, multi-domain co-simulation standards enable combining such distinct ecosystems beyond tool and model boundaries. Based on these concepts, this work presents a joint set of frameworks for virtualizing the ADAS prototyping flow via whole-system simulation. The focus of the work lies in the design of an automotive-flavor virtual platform, ensuring accurate and fast hardware/software simulation. To highlight the advantages of the framework system, two ADAS applications were prototyped in various configurations. Lastly, algorithmic and system-level analyses are presented, alongside simulation performance evaluation.

[1]  Victor M. Peñeñory,et al.  Proposal of a Computer Vision System to Detect and Track Vehicles in Real Time Using an Embedded Platform Enabled with a Graphical Processing Unit , 2015, ICM 2015.

[2]  Frédéric Pétrot,et al.  Facing ADAS validation complexity with usage oriented testing , 2016, ArXiv.

[3]  Ulf Schlichtmann,et al.  Reliability challenges for electric vehicles: From devices to architecture and systems software , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[4]  Diana Göhringer,et al.  Evaluation of driver assistance systems with a car simulator using a virtual and a real FPGA platform , 2013, 2013 Conference on Design and Architectures for Signal and Image Processing.

[5]  Frédéric Pétrot,et al.  Using binary translation in event driven simulation for fast and flexible MPSoC simulation , 2009, CODES+ISSS '09.

[6]  Stefan-Alexander Schneider,et al.  Significant Reduction of Validation Efforts for Dynamic Light Functions with FMI for Multi-Domain Integration and Test Platforms , 2014 .

[7]  Christos Dimitrakakis,et al.  TORCS, The Open Racing Car Simulator, v1.3.5 , 2013 .

[8]  Paolo Gai,et al.  A Software Stack for Next-Generation Automotive Systems on Many-Core Heterogeneous Platforms , 2016, 2016 Euromicro Conference on Digital System Design (DSD).

[9]  Rainer Leupers,et al.  Fully Virtual Rapid ADAS Prototyping via a Joined Multi-domain Co-simulation Ecosystem , 2018, VEHITS.

[10]  Rainer Leupers,et al.  Virtual hardware-in-the-loop co-simulation for multi-domain automotive systems via the functional mock-up interface , 2015 .

[11]  Ivan Tanev,et al.  Evolving a general electronic stability program for car simulated in TORCS , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[12]  Daniele Loiacono,et al.  Searching for the optimal racing line using genetic algorithms , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[13]  Lui Sha,et al.  Priority Inheritance Protocols: An Approach to Real-Time Synchronization , 1990, IEEE Trans. Computers.

[14]  Richard M. Fujimoto,et al.  PROCEEDINGS OF THE 1997 WINTER SIMULATION CONFERENCE , 1997 .

[15]  Fabrice Bellard,et al.  QEMU, a Fast and Portable Dynamic Translator , 2005, USENIX ATC, FREENIX Track.