{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2365"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2365","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"Trailer Articulation Angle Detection and Tracking For Trailer Backup Assistant Systems","abstract":"SUVs and pickup trucks have a significant share of the United States market. This fact has motivated automakers to equip their products with more safety and convenience features, such as the Advanced trailer backup assistance system (TBAS). TBAS helps to take the frustration out of the driver of the tow-vehicle during the backup maneuvers. To operate an autonomous reversing maneuver, the TBAS requires the trailer-tow vehicle combined kinematic model, where a key parameter is the articulation angle between the tow vehicle and the trailer. In this dissertation, we aim to develop three models to detect the articulation angle between tow-vehicle and trailer using the rear-side camera and radar sensors. Models, each designed as an independent module for detecting the trailer articulation angle, are; computer vision-based hitch angle detection, radar-based hitch angle tracking, and deep learning-based RadarRegNet-based hitch angle estimation. The computer vision-based module estimates the relative trailer angle using a deep learning object detection model to detect marker-lights on the trailer. The proposed computer vision model processes the image frames acquired from the rear-facing camera to detect and track the trailer and estimate its orientation to the tow vehicle. The proposed radar-based hitch angle tracking, for the estimate of the hitch angle, processes reflections acquired from the mmWave radars situated at the rear side of the vehicle to detect the trailer and track its orientation in relation to the tow-vehicle. This technique is based on the tracking of individual points in the merged radars point-cloud. Each tracked point is considered as a hitch angle estimator. Using the current and past position information of a point, the model estimates the current hitch angle. Finally, the proposed RadarRegNet-based hitch angle estimation model employs a deep learning image regression convolutional neural network. The network input is an occupancy grid map of the radar points in the merged point-clouds acquired by two radars, and its output is the hitch angle. Aiming for a reasonable inference time for the time-critical hitch angle estimation task, we introduced a modified Inception block. In the proposed modified Inception block to reduce the computational cost by up to 50%.","abstract_html":"SUVs and pickup trucks have a significant share of the United States market. This fact has motivated automakers to equip their products with more safety and convenience features, such as the Advanced trailer backup assistance system (TBAS). TBAS helps to take the frustration out of the driver of the tow-vehicle during the backup maneuvers. To operate an autonomous reversing maneuver, the TBAS requires the trailer-tow vehicle combined kinematic model, where a key parameter is the articulation angle between the tow vehicle and the trailer. In this dissertation, we aim to develop three models to detect the articulation angle between tow-vehicle and trailer using the rear-side camera and radar sensors. Models, each designed as an independent module for detecting the trailer articulation angle, are; computer vision-based hitch angle detection, radar-based hitch angle tracking, and deep learning-based RadarRegNet-based hitch angle estimation. The computer vision-based module estimates the relative trailer angle using a deep learning object detection model to detect marker-lights on the trailer. The proposed computer vision model processes the image frames acquired from the rear-facing camera to detect and track the trailer and estimate its orientation to the tow vehicle. The proposed radar-based hitch angle tracking, for the estimate of the hitch angle, processes reflections acquired from the mmWave radars situated at the rear side of the vehicle to detect the trailer and track its orientation in relation to the tow-vehicle. This technique is based on the tracking of individual points in the merged radars point-cloud. Each tracked point is considered as a hitch angle estimator. Using the current and past position information of a point, the model estimates the current hitch angle. Finally, the proposed RadarRegNet-based hitch angle estimation model employs a deep learning image regression convolutional neural network. The network input is an occupancy grid map of the radar points in the merged point-clouds acquired by two radars, and its output is the hitch angle. Aiming for a reasonable inference time for the time-critical hitch angle estimation task, we introduced a modified Inception block. In the proposed modified Inception block to reduce the computational cost by up to 50%.","abstract_has_math":false,"creators":["Bahramgiri, Mojtaba"],"institution":null,"degree_name":"Doctor of Philosophy in Electrical Engineering (PhD)","degree_level":"Campus Access Dissertation","degree_discipline":"Department of Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Saeid Nooshabadi","Glen Archer"],"advisors":[],"committee_chairs":[],"committee_members":["Daniel Fuhrmann","Jeremy Bos"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:18:18Z","subjects":["Deep learning","CNN object detection and tracking","radar point cloud processing","radar-based object tracking","Artificial Intelligence and Robotics","Signal Processing"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1281"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1281","href":"https://digitalcommons.mtu.edu/etdr/1281","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1281","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1281","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2365","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Saeid Nooshabadi","Glen Archer"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Daniel Fuhrmann","Jeremy Bos"]},{"key":"dc:creator","label":"Author","values":["Bahramgiri, Mojtaba"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-04-01T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2021-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Campus Access Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy in Electrical Engineering (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep learning","CNN object detection and tracking","radar point cloud processing","radar-based object tracking","Artificial Intelligence and Robotics","Signal Processing"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1281","https://digitalcommons.mtu.edu/etdr/1281"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["SUVs and pickup trucks have a significant share of the United States market. This fact has motivated automakers to equip their products with more safety and convenience features, such as the Advanced trailer backup assistance system (TBAS). TBAS helps to take the frustration out of the driver of the tow-vehicle during the backup maneuvers. To operate an autonomous reversing maneuver, the TBAS requires the trailer-tow vehicle combined kinematic model, where a key parameter is the articulation angle between the tow vehicle and the trailer. In this dissertation, we aim to develop three models to detect the articulation angle between tow-vehicle and trailer using the rear-side camera and radar sensors. Models, each designed as an independent module for detecting the trailer articulation angle, are; computer vision-based hitch angle detection, radar-based hitch angle tracking, and deep learning-based RadarRegNet-based hitch angle estimation. The computer vision-based module estimates the relative trailer angle using a deep learning object detection model to detect marker-lights on the trailer. The proposed computer vision model processes the image frames acquired from the rear-facing camera to detect and track the trailer and estimate its orientation to the tow vehicle. The proposed radar-based hitch angle tracking, for the estimate of the hitch angle, processes reflections acquired from the mmWave radars situated at the rear side of the vehicle to detect the trailer and track its orientation in relation to the tow-vehicle. This technique is based on the tracking of individual points in the merged radars point-cloud. Each tracked point is considered as a hitch angle estimator. Using the current and past position information of a point, the model estimates the current hitch angle. Finally, the proposed RadarRegNet-based hitch angle estimation model employs a deep learning image regression convolutional neural network. The network input is an occupancy grid map of the radar points in the merged point-clouds acquired by two radars, and its output is the hitch angle. Aiming for a reasonable inference time for the time-critical hitch angle estimation task, we introduced a modified Inception block. In the proposed modified Inception block to reduce the computational cost by up to 50%."]},{"key":"dc:description.note","label":"Dc Description Note","values":["<p>As Dr. Nooshabadi has mentioned in the \" Approval of a Dissertation, Thesis, or Report\", we don't want this to go public until next year, as we are considering filing for patents.</p>"]},{"key":"dc:title","label":"Title","values":["Trailer Articulation Angle Detection and Tracking For Trailer Backup Assistant Systems"]}]}],"canonical_facts":{"dc:contributor":["Saeid Nooshabadi","Glen Archer"],"dc:contributor.committeemember":["Daniel Fuhrmann","Jeremy Bos"],"dc:creator":["Bahramgiri, Mojtaba"],"dc:date.available":["2022-04-01T07:00:00Z"],"dc:date.created":["2021-01-01T08:00:00Z"],"dc:description.abstract":["SUVs and pickup trucks have a significant share of the United States market. This fact has motivated automakers to equip their products with more safety and convenience features, such as the Advanced trailer backup assistance system (TBAS). TBAS helps to take the frustration out of the driver of the tow-vehicle during the backup maneuvers. To operate an autonomous reversing maneuver, the TBAS requires the trailer-tow vehicle combined kinematic model, where a key parameter is the articulation angle between the tow vehicle and the trailer. In this dissertation, we aim to develop three models to detect the articulation angle between tow-vehicle and trailer using the rear-side camera and radar sensors. Models, each designed as an independent module for detecting the trailer articulation angle, are; computer vision-based hitch angle detection, radar-based hitch angle tracking, and deep learning-based RadarRegNet-based hitch angle estimation. The computer vision-based module estimates the relative trailer angle using a deep learning object detection model to detect marker-lights on the trailer. The proposed computer vision model processes the image frames acquired from the rear-facing camera to detect and track the trailer and estimate its orientation to the tow vehicle. The proposed radar-based hitch angle tracking, for the estimate of the hitch angle, processes reflections acquired from the mmWave radars situated at the rear side of the vehicle to detect the trailer and track its orientation in relation to the tow-vehicle. This technique is based on the tracking of individual points in the merged radars point-cloud. Each tracked point is considered as a hitch angle estimator. Using the current and past position information of a point, the model estimates the current hitch angle. Finally, the proposed RadarRegNet-based hitch angle estimation model employs a deep learning image regression convolutional neural network. The network input is an occupancy grid map of the radar points in the merged point-clouds acquired by two radars, and its output is the hitch angle. Aiming for a reasonable inference time for the time-critical hitch angle estimation task, we introduced a modified Inception block. In the proposed modified Inception block to reduce the computational cost by up to 50%."],"dc:description.note":["<p>As Dr. Nooshabadi has mentioned in the \" Approval of a Dissertation, Thesis, or Report\", we don't want this to go public until next year, as we are considering filing for patents.</p>"],"dc:identifier":["10.37099/mtu.dc.etdr/1281","https://digitalcommons.mtu.edu/etdr/1281"],"dc:subject":["Deep learning","CNN object detection and tracking","radar point cloud processing","radar-based object tracking","Artificial Intelligence and Robotics","Signal Processing"],"dc:title":["Trailer Articulation Angle Detection and Tracking For Trailer Backup Assistant Systems"],"thesis:degree_discipline":["Department of Electrical and Computer Engineering"],"thesis:degree_level":["Campus Access Dissertation"],"thesis:degree_name":["Doctor of Philosophy in Electrical Engineering (PhD)"]},"updated_at":"2026-11-19T08:18:18Z"}