An Approach to Integrating Data Fusion into Advanced Driver Assistance Systems (ADAS)

Abstract

Demand for the development of Advanced Driver Assistance System (ADAS) is created by the desire to build safer vehicles and roads, and thus to reduce the number of road fatalities and legislation of the leading country. Since ADAS and automated vehicles require much more complex sensory input, the automotive industry faces a great challenge in turning autonomous driving into a reality. As a result, ADAS requires special methods to handle multiple sensory inputs, such as Data Fusion Algorithm. This white paper presents an approach to integrating data fusion into an ADAS.

Table of Content:

1. Introduction

2. Sensors Overview

2.1. Sensor Fusion

2.2. Automotive Sensor Fusion

3. Architectures for Sensor Data Fusion

3.1. Monolithic Data Fusion Architecture

3.2. Centralized Data Fusion Architecture

3.3. Distributed Fusion Architecture

4. An approach to integrating data fusion into ADAS SOCs (System-On-Chips)

5. Conclusion

ADAS-datafusion