Analysis of the Effects of Perception Errors in ADAS Systems via Monte Carlo Simulations


Staff Mentor:

prof. J. Hellendoorn


Other Mentor(s):

Dr. Arturo Tejada Ruiz (TNO)

Keywords:

Intelligent control; Learning and adaptive control; Optics and imaging

Description:

Introduction

The Integrated Vehicle Safety (IVS) department at TNO develops technology for automated driving and cooperative mobility for intelligent vehicle applications. An important aspect in all such applications (truck platooning, autonomous cars, etc.) is the ability of the vehicle to recognize and represent its environment. This is generally accomplished through an array of onboard sensors, such as cameras or LIDARS, combined with advanced data processing algorithms.

The output of such perception systems is used at several levels of an intelligent vehicle control structure to perform tasks such as automated lane changing, lane keeping and/or platooning. Although it is generally known that inaccurate perception systems could lead to large vehicle control errors, the sensitivity of the control system to perception inaccuracies is not yet well understood.

Assignment description

The main goal of this assignment is to develop a Matlab/Simulink-based Monte Carlo simulation suit for the evaluation of the perception system requirements (accuracy, precision, latencies, frame rates, etc.) necessary to support both longitudinal and lateral vehicle control.

Main Elements

• Monte Carlo simulation suit should make use of the current TNO vehicle control models

• The test should take into account different perception modes (cameras, radars, etc.) and different driving scenarios.

• The test may require field work.

Added value

For the project:

• Characterization of perception requirements for intelligent vehicle automation applications

For the intern:

• Know how on visual perception systems for intelligent vehicle applications

• Know how on current control systems in current intelligent vehicles

• Working in a dynamic environment on automated driving functions

© Copyright Delft Center for Systems and Control, Delft University of Technology, 2017.