This paper offers recent ideas and its implementation on leveraging AI for off highway Autonomous vehicle Simulations in SIL and HIL frameworks. Our objective is to enhance software quality and reliability while reducing costs and efforts through advanced simulation techniques.We employed multiple innovative solutions to build a System of Systems Simulation. Physics based models are a prerequisite for detailed and accurate representation of the real-world system, but it poses challenges due to its computational complexity and storage requirements. Machine learning algorithms were used to create surrogate/reduced order models to optimize by preserving the expected fidelity of models. It helped to speed up simulation and compile model code for SIL HIL Targets.Built AI driven interfaces to bridge windows, Linux and Mobile Operating systems. Time synchronization was the key challenge as multiple environments were needed for end-to-end solutions. This was resolved by reinforcement learning optimization algorithms so that loss of information can be prevented. John Deere Operations Center™ Fleet management was integrated with vehicle simulators so that remote monitoring and control of machine configurations and settings for various autonomy mode could be validated in virtual environment.Gen AI based tools were used for creation of Test plan and its Automation to accumulate several hundred hours of test execution for autonomy related features. The team tested various SW HW fault conditions to understand the impact and behavior of the system in autonomy mode. As part of the next steps this framework would be further scaled for future autonomy programs and product linesThis adoption of AI-based methods has expedited the delivery of autonomous vehicles, ensuring they are technologically advanced and customized to meet customer needs.
Karegaonkar et al. (Thu,) studied this question.