Machine learning for autonomous vehicle's trajectory prediction: A comprehensive survey, challenges, and future research directions

The significant contribution of human errors, accounting for approximately 94% (with a margin of ±2.2%), to road crashes leading to casualties, vehicle damages, and safety concerns necessitates the exploration of alternative approaches. Autonomous Vehicles (AVs) have emerged as a promising solution by replacing human drivers with advanced computer-aided decision-making systems. However, for AVs to effectively navigate the road, they must possess the capability to predict the future behavior of nearby traffic participants, similar to the predictive driving abilities of human drivers. Building upon existing literature is crucial to advance the field and develop a comprehensive understanding of trajectory prediction methods in the context of automated driving. To address this need, the authors have undertaken a comprehensive review that focuses on trajectory prediction methods for AVs, with a particular emphasis on machine learning techniques including deep learning and reinforcement learning-based approaches. They have extensively examined over two hundred studies related to trajectory prediction in the context of AVs. The paper begins with an introduction to the general problem of predicting vehicle trajectories and provides an overview of the key concepts and terminology used throughout. After providing a brief overview of conventional methods, this review conducts a comprehensive evaluation of several deep learning-based techniques. Each method is summarized briefly, accompanied by a detailed analysis of its strengths and weaknesses. The discussion further extends to reinforcement learning-based methods. This article also examines the various datasets and evaluation metrics that are commonly used in trajectory prediction tasks. Encouraging an unbiased and objective discussion, they compare two major learning processes, considering specific functional features. By identifying challenges in the existing literature and outlining potential research directions, this review significantly contributes to the advancement of knowledge in the domain of AV trajectory prediction. Its primary objective is to streamline current research efforts and offer a futuristic perspective, ultimately benefiting future developments in the field.

• Record URL:
  https://doi.org/10.1016/j.vehcom.2024.100733
• Record URL:
  http://www.sciencedirect.com/science/article/pii/S2214209624000081
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/22142096
• Supplemental Notes:
  • © 2024 Published by Elsevier Inc. Abstract reprinted with permission of Elsevier.
• Authors:
  • Bharilya, Vibha
  • 0009-0009-0699-3908
  • Kumar, Neetesh
• Publication Date: 2024-4

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References; Tables;
• Pagination: 100733
• Serial:
  • Vehicular Communications
  • Volume: 46
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 2214-2096
  • Serial URL: http://www.sciencedirect.com/science/journal/22142096/1/2

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Machine learning; Predictive models; Vehicle safety; Vehicle trajectories
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01907556
• Record Type: Publication
• Files: TRIS
• Created Date: Feb 7 2024 4:55PM