Characterization of Neural Networks Automatically Mapped on Automotive-grade Microcontrollers
This work addresses the challenge of deploying neural networks on resource-constrained automotive-grade microcontrollers, enabling edge computing applications in vehicles.
The paper presents a framework for implementing neural network models on automotive microcontrollers, demonstrating its efficiency in two vehicle applications: intrusion detection on the Controller Area Network bus and residual capacity estimation in Lithium-Ion batteries for electric vehicles.
Nowadays, Neural Networks represent a major expectation for the realization of powerful Deep Learning algorithms, which can determine several physical systems' behaviors and operations. Computational resources required for model, training, and running are large, especially when related to the amount of data that Neural Networks typically need to generalize. The latest TinyML technologies allow integrating pre-trained models on embedded systems, allowing making computing at the edge faster, cheaper, and safer. Although these technologies originated in the consumer and industrial worlds, many sectors can greatly benefit from them, such as the automotive industry. In this paper, we present a framework for implementing Neural Network-based models on a family of automotive Microcontrollers, showing their efficiency in two case studies applied to vehicles: intrusion detection on the Controller Area Network bus and residual capacity estimation in Lithium-Ion batteries, widely used in Electric Vehicles.