Topical Report: AI in Automotive

AI Report Cover - Square.jpg
AI Report Cover - Square.jpg

Topical Report: AI in Automotive

5,000.00

Automated driving is the perfect use case for artificial intelligence (AI), because algorithms leveraging AI can handle situations that the vehicle has not been explicitly trained on. In other words, AI, unlike classical (non-AI) algorithms, is capable of leveraging knowledge gained from one set of situations to tackle the potentially limitless situations that an autonomous car may encounter. This is known as generalization and is not often found in classical algorithms.

There are many ways AI is being applied within the advanced driver assistant systems (ADAS) and automated driving space. This report provides a general overview of AI and examines the use cases of AI in automotive applications, the challenges of AI-trained algorithms, and key players in the AI ecosystem within the context of automotive. The report also discusses how VSI Labs has applied AI in its own research vehicle.

Add To Cart

Table of Contents

  • Introduction

  • Section 1 - AI Applied to Automotive

    • What is AI

      • Artificial Neural Networks

      • Deep Neural Networks

      • Convolutional Neural Networks

    • AI in Automotive

      • AI Training

      • Overfitting

      • Validating and Testing AI-based Algorithms

    • Automotive AI Use Cases - Perception

      • AI for Object Detection

      • AI for Object Classification

      • AI for Traffic Sign Recognition

      • Lane Detection

      • Free-Space Detection (Drivable road calculation)

      • Pixel level Semantic Segmentation

    • Automotive AI Use Cases - Predictive Control

      • Deep Reinforcement Learning

      • Object Trajectory/Prediction

      • End-to-End Automation

    • Automotive AI Use Cases - Driver Monitoring Applications

    • Automotive AI Use Cases in VSI’s AV Stack

      • Lane Keeping

      • Lane Changing & Postprocessing with Classical Algorithms

    • How VSI Has Trained, Validated and Tested AI-based Algorithms

      • Training Process and Metrics

      • Evaluation of Training and Validation

    • Challenges of AI

  • Section 2 - The AI Value Chain

    • Training Datasets

    • Deep learning Frameworks and Tools

    • Processors for AI Training and Inferencing

      • Training Processors

      • Embedded Processors

      • Inference Model Generators

    • AI Software/Middleware

      • Baidu Apollo

      • Elektrobit Ribons

      • Nvidia Driveworks

      • TierIV Autoware

      • AI Software Startups

    • AI R&D Activities by OEMs

      • American OEMs

      • European OEMs

      • Asian OEMs

    • AI R&D Activities by Automotive Supplier/Tier 1

    • AI R&D Activities by Mobility Companies

  • Conclusion