Adaptive methods for robust commercial vehicle control Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/1v53k057r

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • This thesis explores the implementation of learning based control with predictive cruise control and the potential this technology has for increasing fuel efficiency while keeping on a well maintained schedule for commercial trucks. Traditional cruise control is wasteful when maintaining a constant velocity over rolling hills. Predictive cruise control is able to look ahead at future road conditions and solve for a cost effective course of action. Model based controllers have been implemented in this field but cannot accommodate all the complexities of a dynamic environment such as a stretch of highway in variable conditions. In this work, we focus on incorporating a learner into an already successful model based predictive cruise controller in order to improve its performance. We explore back propagating neural networks using several different input representations of varying complexity in order to predict future errors then take actions to prevent said errors from occurring. The results show that we are able to improve upon the model based predictive cruise controller by up to 60% average across the data. To obtain the best improvement it was found that highly descriptive inputs must be used in conjunction with training data that is very representative of the testing data. To obtain a more robust controller that can perform well on all terrain, use inputs that present less information and more generalizations to the neural network.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Language
Replaces
Additional Information
  • description.provenance : Submitted by Jaime Junell (junellj@onid.orst.edu) on 2009-08-13T18:31:25Z No. of bitstreams: 1 Junell_MSthesis_final_nb.pdf: 1680047 bytes, checksum: d604f755b91d1a9be27f01a5c61cae27 (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2009-08-17T16:44:10Z (GMT) No. of bitstreams: 1 Junell_MSthesis_final_nb.pdf: 1680047 bytes, checksum: d604f755b91d1a9be27f01a5c61cae27 (MD5)
  • description.provenance : Approved for entry into archive by Linda Kathman(linda.kathman@oregonstate.edu) on 2009-08-17T22:58:56Z (GMT) No. of bitstreams: 1 Junell_MSthesis_final_nb.pdf: 1680047 bytes, checksum: d604f755b91d1a9be27f01a5c61cae27 (MD5)
  • description.provenance : Made available in DSpace on 2009-08-17T22:58:56Z (GMT). No. of bitstreams: 1 Junell_MSthesis_final_nb.pdf: 1680047 bytes, checksum: d604f755b91d1a9be27f01a5c61cae27 (MD5)

Relationships

In Administrative Set:
Last modified: 08/07/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items