Towards a Functional System Architecture for Automated Vehicles

Abstract

This paper presents a functional system architecture for an automated vehicle. It provides an overall, generic structure that is independent of a specific implementation of a particular vehicle project. Yet, it has been inspired and cross-checked with a real world automated driving implementation in the Stadtpilot project at the Technische Universität Braunschweig. The architecture entails aspects like environment and self perception, planning and control, localization, map provision, Vehicle-To-X-communication, and interaction with human operators.

Submitted for review to IEEE Transactions on Intelligent Transportation Systems, 16 pages, 4 figures

Cited by in corpus (11)

• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• A Review of Testing Object-Based Environment Perception for Safe Automated Driving
• A Taxonomy to Unify Fault Tolerance Regimes for Automotive Systems: Defining Fail-Operational, Fail-Degraded, and Fail-Safe
• Overview of Tools Supporting Planning for Automated Driving
• Situation-Aware Environment Perception Using a Multi-Layer Attention Map
• A Rational Agent Controlling an Autonomous Vehicle: Implementation and Formal Verification
• Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving
• Toward Generating Sufficiently Valid Test Case Results: A Method for Systematically Assigning Test Cases to Test Bench Configurations in a Scenario-Based Test Approach for Automated Vehicles
• Compensating for the Absence of a Required Accompanying Person: A Draft of a Functional System Architecture for an Automated Vehicle
• A Method for Classifying Test Bench Configurations in a Scenario-Based Test Approach for Automated Vehicles
• Resilient Sensor Architecture Design and Tradespace Analysis for Autonomous Vehicle Localization and Mapping