Sensor Health Monitoring for Autonomous Vehicles

Institute

Lehrstuhl für Fahrzeugtechnik (TUM-ED)

Type

Bachelor's Thesis / Semester Thesis /

Content

experimental /  

Description

MOTIVATION

Reliable perception is a prerequisite for automated driving. Localization, mapping, and environment understanding all depend on the assumption that sensors such as LiDAR, radar, and cameras deliver trustworthy data. In real operation, however, sensors degrade: channels may fail, measurements drift, calibration changes, or parts of the field of view become occluded. These effects often remain unnoticed while they silently increase uncertainty and may ultimately compromise safety. Thereofre, sensor health monitoring is a crucial part of fault tolerance for Autonomous Vehicles (AV) to measure the current sensor's performance capacity and to initiate recovery mechanisms.

Requirements

YOUR ROLE

This thesis contributes to the development and validation of a sensor health monitoring system for our research vehicle EDGAR. EDGAR contains different sensor modalities like LiDAR, GPS and cameras. Your main tasks will be to derive and implement metrics and mechanisms to determine the health state of the vehicle. With a well chosen validation strategy, your concept shall be validated thorougly and tested. The results shall be analyzed and discussed. 

• Literature research on "Sensor Fault Tolerance", "Sensor Health", "LiDAR/Camera/GPS Monitoring"
• Conceptualize a sensor health monitoring architecture for EDGAR
• Define suitable validation strategy with suitable scenarios
• Implement the sensor healt monitoring architecture and the validation strategy
• Analysis of data and documentation of results

WHAT YOU SHOULD BRING ALONG

• Strong Motivation and Interest for AVs
• Basic Knowledge in Programming, e. g. Python, C++
• Structured and independent way of working

If you are interested in joining this project, feel free to send me an application with your CV and transcript of records. I look forward to receive your application.

Verwendete Technologien

Autonomous Driving, Safety, ROS2

Tags

FTM Studienarbeit, FTM AV, FTM AV Safe Operation, FTM Karunainayagam

Possible start

sofort

Contact

Nijinshan Karunainayagam, M. Eng.
Room: MW3507
Phone: +49 89 289 15386
nijinshan.karunainayagamtum.de