國立高雄大學圖資館 |

Language: English

Back

Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model /Jason A Sexton.
Author:	Sexton, Jason A.,
Description:	1 electronic resource (112 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
Notes:	Advisors: Abraham, Noran Committee members: Akinfaderin, Adewale; Etemadi, Amir.
Contained By:	Dissertations Abstracts International87-06B.
Subject:	Computer engineering.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32286101
ISBN:	9798265454263

Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model /
Sexton, Jason A.,

Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model /Jason A Sexton. - 1 electronic resource (112 pages)

Source: Dissertations Abstracts International, Volume: 87-06, Section: B.

From January to June 2025, 17,140 vehicular crash-related deaths occurred within the United States. Traffic growth within the nation is expected to increase by 1.5% from 2025 to 2027, with an anticipated 26% growth in the U.S. population leading to a 72% increase in passenger miles per year. While autonomous driving vehicles and intelligent driving systems reduce congestion and accidents, many car manufacturers cannot afford the cost of entry due to high-value systems such as LiDAR and on-board cameras. This limited presence of autonomous vehicles raises the risk of vehicular accidents. Moreover, most autonomous vehicles only predict 3-5 seconds out to mitigate immediate accident avoidance, leading to growing traffic congestion, increased accidents on roadways, and impacts on other fields such as urban planning and emergency services.The Georgia Department of Vehicle Services (2025) stated that most good drivers make driving decisions 12-15 seconds ahead of action. However, to date, research has been solely focused on near-term, 3-5-second predictions for vehicle trajectories, with almost no research extending to long-term predictions of 6-10 seconds. In this paper, by combining contrastive language image pretraining (CLIP) with diffusion models, which typically analyze multiple possible futures, we holistically examine long-term vehicle trajectories and introduce human-like intuition into multi-modal models to discern if visual and semantic information improve trajectory predictions over time.This praxis examens two research questions: 1) How does the proposed model perform against other state of the art models (SOTA)? 2) How do adjustments in CLIP architecture and training impact the final average displacement error (ADE)? The research showed that the model performed within one standard deviation of similar models and that the more robust the CLIP labeling, the greater impact on the performance of the model.

English

ISBN: 9798265454263Subjects--Topical Terms:

212944
Computer engineering.
Subjects--Index Terms:

Contrastive language image pretraining

Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model /
LDR:03513nmm a22004453i 4500 001 693784
005 20260511063024.5
006 m o d
007 cr|nu||||||||
008 260819s2026 miu||||||m |||||||eng d
020 $a 9798265454263
035 $a (MiAaPQD)AAI32286101
035 $a AAI32286101
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Sexton, Jason A., $e author. $3 1010463
245 1 0 $a Predicting Long-Term Vehicle Trajectories Combining Contrastive Language - Image Pretraining (CLIP) Into a Diffusion Model / $c Jason A Sexton.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2026
300 $a 1 electronic resource (112 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
500 $a Advisors: Abraham, Noran Committee members: Akinfaderin, Adewale; Etemadi, Amir.
502 $b D.Engr. $c The George Washington University $d 2026.
520 $a From January to June 2025, 17,140 vehicular crash-related deaths occurred within the United States. Traffic growth within the nation is expected to increase by 1.5% from 2025 to 2027, with an anticipated 26% growth in the U.S. population leading to a 72% increase in passenger miles per year. While autonomous driving vehicles and intelligent driving systems reduce congestion and accidents, many car manufacturers cannot afford the cost of entry due to high-value systems such as LiDAR and on-board cameras. This limited presence of autonomous vehicles raises the risk of vehicular accidents. Moreover, most autonomous vehicles only predict 3-5 seconds out to mitigate immediate accident avoidance, leading to growing traffic congestion, increased accidents on roadways, and impacts on other fields such as urban planning and emergency services.The Georgia Department of Vehicle Services (2025) stated that most good drivers make driving decisions 12-15 seconds ahead of action. However, to date, research has been solely focused on near-term, 3-5-second predictions for vehicle trajectories, with almost no research extending to long-term predictions of 6-10 seconds. In this paper, by combining contrastive language image pretraining (CLIP) with diffusion models, which typically analyze multiple possible futures, we holistically examine long-term vehicle trajectories and introduce human-like intuition into multi-modal models to discern if visual and semantic information improve trajectory predictions over time.This praxis examens two research questions: 1) How does the proposed model perform against other state of the art models (SOTA)? 2) How do adjustments in CLIP architecture and training impact the final average displacement error (ADE)? The research showed that the model performed within one standard deviation of similar models and that the more robust the CLIP labeling, the greater impact on the performance of the model.
546 $a English
590 $a School code: 0075
650 4 $a Computer engineering. $3 212944
650 4 $a Computer science. $3 199325
650 4 $a Information technology. $3 184390
653 $a Contrastive language image pretraining
653 $a Diffusion models
653 $a Trajectories
653 $a Transformers
653 $a Average displacement error
690 $a 0800
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a The George Washington University. $b Systems Engineering. $e degree granting institution. $3 990046
720 1 $a Abraham, Noran $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-06B.
790 $a 0075
791 $a D.Engr.
792 $a 2026
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32286101