{"id":236,"date":"2019-07-11T19:43:52","date_gmt":"2019-07-12T02:43:52","guid":{"rendered":"https:\/\/blogs.plm.automation.siemens.com\/t5\/Digital-Transformations\/HLS-verifies-artificial-intelligence-for-ADAS-in-autonomous-cars\/ba-p\/608942"},"modified":"2026-03-26T12:04:26","modified_gmt":"2026-03-26T16:04:26","slug":"hls-verifies-artificial-intelligence-for-adas-in-autonomous-cars","status":"publish","type":"post","link":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/hls-verifies-artificial-intelligence-for-adas-in-autonomous-cars\/","title":{"rendered":"HLS verifies artificial intelligence for ADAS in autonomous cars"},"content":{"rendered":"

Artificial Intelligence (AI) involves the use of neural networks and you might have heard of terms like CNNs, DCNs, GANs, SNNs and wonder what they mean. Fundamentally, they are nothing but a set of algorithms that are designed to recognize patterns. These algorithms help cluster and classify huge volumes of data.<\/P><\/p>\n

Here are a few popular neural networks in the AI space; each has at least some relevance to work on ADAS and automated driving applications:<\/P><\/p>\n

Recurrent Neural Networks (RNNs<\/U>): Connections between nodes for a directed graph along a temporal sequence \u2013 for pattern recognition such as handwriting or speech recognition<\/P><\/p>\n

Deep Convolution Network (DCNs):<\/U> Analogous to the connectivity pattern of neurons in the human brain, specifically inspired by the visual cortex \u2013 for pattern recognition for image, video and natural language processing<\/P><\/p>\n

Generative Adversarial Network (GANs):<\/U> Two neural networks contesting with each other in a game theory exercise \u2013 used to generate photorealistic images<\/P><\/p>\n

Spiking Neural Network (SNNs): <\/U>Mimics natural neural networks and includes the concept of time along with neuronal and synaptic states \u2013 for information processing and modeling of the central nervous system<\/P><\/p>\n

Beyond AI, driving without human intervention requires a sophisticated framework of image sensors. These sensors include LiDAR, Radar and cameras, which together continuously generate a high volume of data in real time about the environment surrounding the car. Neural networks help the car create meaningful information about this data and react in real-time.<\/P><\/p>\n

Implementing machine learning (ML) algorithms in hardware is challenging. To achieve accuracy, an inference chip for autonomous vehicle needs to address the following challenges:<\/P><\/p>\n


    \n
  1. Performance:<\/U> A single high definition camera can capture a 1920×1080 image at 60 frames per second; a car can have 10 or more such cameras<\/LI>
    \n
  2. Power:<\/U> AI inference can a massively power-intensive operation, especially because of the high volume of accesses to remote memories<\/LI>
    \n
  3. Functional Safety:<\/U> Safety is the overarching and comprehensive requirement, so the need to detect functional safety issues that might creep in because of various hardware faults can also command significant compute resources<\/LI>
    \n<\/OL>
    \n

    The biggest challenge in creating such a chip is the turnaround time for the traditional ASIC design flow. It takes somewhere from several months to a year to implement a new ASIC hardware.<\/P>
    \n

    My colleague, David Fritz, talks through the basic steps in creating an inferencing engine in this interview<\/A> with Semiconductor Engineering editor Ed Sperling.<\/P><\/p>\n

    <\/p>\n