Watch out, pothole! Featuring Road Damage Detection in an End-to-end System for Autonomous Driving

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

While autonomous driving technology made significant progress in the last decade, road damage detection as a relevant challenge for ensuring safety and comfort is still under development. This paper addresses the lack of algorithms for detecting road damages that meet autonomous driving systems’ requirements. We investigate the environmental perception systems’ architecture and current algorithm designs for road damage detection. Based on the autonomous driving architecture, we develop an end-to-end concept that leverages data from low-cost pre-installed sensors for real-time road damage and damage severity detection as well as cloud- and crowd-based HD Feature Maps to share information across vehicles. In a design science research approach, we develop three artifacts in three iterations of expert workshops and design cycles: the end-to-end concept featuring road damages in the system architecture and two lightweight deep neural networks, one for detecting road damages and another for detecting their severity as the central components of the system. The research design draws on new self-labeled automotive-grade images from front-facing cameras in the vehicle and interdisciplinary literature regarding autonomous driving architecture and the design of deep neural networks. The road damage detection algorithm delivers cutting-edge performance while being lightweight compared to the winners of the IEEE Global Road Damage Detection Challenge 2020, which makes it applicable in autonomous vehicles. The road damage severity algorithm is a promising approach, delivering superior results compared to a baseline model. The end-to-end concept is developed and evaluated with experts of the autonomous driving application domain.
Original languageEnglish
Article number102091
JournalData and Knowledge Engineering
Volume142
ISSN0169-023X
DOIs
Publication statusPublished - 01.11.2022

Bibliographical note

Publisher Copyright:
© 2022 Elsevier B.V.

Recently viewed

Publications

  1. Sustainable Statehood: Reflections on Critical (Pre-)Conditions, Requirements and Design Options
  2. Rolling In The Deep
  3. Bimodal Enterprise Architecture Management
  4. Measuring mathematics competence in international and national large scale assessments
  5. One step forward, two steps back
  6. Effect of Welding Speed on Friction Stir Welds of PM2000 Alloy
  7. Web-Based Stress Management Program for University Students in Indonesia
  8. Religious Loyality and Acceptance of Corruption.
  9. The Power and Peril of Precise vs. Round Health Message Interventions to Increase Stair-Use
  10. Introduction to the symposium on feminist perspectives on human–nature relations
  11. Ansparabschreibung durch Existenzgründer
  12. All Along the Data Watch Tower.
  13. As You Like It
  14. Vorstellungsänderung
  15. Assessment of age-correlated occupational strain as a prerequisite for age-appropriate work organization
  16. New ways in engineering education for a sustainable and smart future
  17. Ecology: Mammals, interaction networks and the relevance of scale
  18. Group evaluations as self-group distancing
  19. Bimodal IT
  20. Does Social Exclusion Improve Detection of Real and Fake Smiles?
  21. C.S.ルイス 「ライオンと魔女」の謎を解く―ナルニアガイド
  22. Trusting as a 'Leap of Faith': Trust-Building Practices in Client-Consultant Relationships
  23. Human development and the "explosion" of democracy
  24. The effects of pre-intervention mindset induction on a brief intervention to increase risk perception and reduce alcohol use among university students
  25. In the Aftermath of Violence. On Being Present and Calling Into Presence
  26. Lifelong learning in practice at Leuphana University