University of Illinois Urbana-Champaign

Perception and sensor fusion in environments with uncertainty using Fuzzy Inference Systems

Sang, I-Chen

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/129482

Description

Title
Perception and sensor fusion in environments with uncertainty using Fuzzy Inference Systems
Author(s)
Sang, I-Chen
Issue Date
2025-01-10
Director of Research (if dissertation) or Advisor (if thesis)
Norris, William R
Doctoral Committee Chair(s)
Norris, William R
Committee Member(s)
  • Sreenivas, Ramavarapu S
  • Hsiao-Wecksler, Elizabeth T
  • Beck, Carolyn L
Department of Study
Industrial&Enterprise Sys Eng
Discipline
Systems & Entrepreneurial Engr
Degree Granting Institution
University of Illinois Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
  • adaptive
  • lane detection
  • AUV
  • autonomous vehicle
  • image processing
  • parameter-tuning
  • navigation
  • drivable region detection
  • CNN
  • adverse weather
Abstract
The escalating significance of autonomous vehicles in the realm of engineering underscores the pressing need for robust systems. Variations in weather conditions pose formidable challenges to on-road systems, while underwater vehicles contend with fluctuating sea currents and variable illumination levels, profoundly impacting their performance. Fuzzy Inference Systems (FIS), also referred to as expert systems, are widely employed in control applications. Their inherent probabilistic nature equips them to stabilize controllers and mitigate errors amidst noise. However, their application to perception, image, and point cloud data is still in its early stages. Thus, this dissertation concentrates on enhancing the perception and sensor fusion capabilities of autonomous vehicles within uncertain environments, leveraging FIS. This work encompasses three principal studies. Initially, a FIS was seamlessly integrated into an adaptive image-sonar sensor fusion framework, steering an Autonomous Underwater Vehicle through pipeline following/inspection tasks. Subsequently, FIS was integrated with image perception frameworks, fine-tuning intrinsic parameters in image processing algorithms to bolster lane detection in on-road vehicles facing adverse weather conditions. Lastly, FIS was deployed in a pixel-wise image-LiDAR sensor fusion framework, generating drivable region detection outcomes for on-road vehicles navigating snowy and rainy conditions. This dissertation presents three major contributions stemming from the fusion of FIS and perception algorithms. First, integrating FIS into sensor fusion navigation frameworks enhances the system noise tolerance. Second, embedding FIS within the parameter-tuning mechanism of image-processing algorithms broadens the scope of applications for perception algorithms. Finally, leveraging FIS and integration with sensor fusion-based drivable region detection marks a significant advancement in autonomous vehicle navigation under challenging environmental conditions.
Graduation Semester
2025-05
Type of Resource
Thesis
Handle URL
https://hdl.handle.net/2142/129482
Copyright and License Information
Copyright 2025 I-Chen Sang

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois