Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Literature Review on Maneuver-Based Scenario Description for Automated Driving Simulations

Nicole Neis, Juergen Beyerer

TL;DR

The paper addresses the need for robust validation of automated driving systems beyond field tests by exploring maneuver-based scenariodescription for resimulation. It surveys resimulation approaches, maneuver detection/prediction/classification, and trajectory prediction/modeling to assess how high-level maneuvers can enable scalable scenario variation while maintaining consistency with submicroscopic vehicle behavior. A key finding is that maneuver-based resimulation remains rare (only a few studies), highlighting a gap in semantic maneuver sets, trigger mechanisms, and integration with detailed vehicle dynamics. The work argues for combining high-level maneuver descriptions with submicroscopic models and environment-aware triggers to improve realism and transferability in simulation-based safety validation. Overall, the paper maps existing foundations and identifies concrete research directions to advance maneuver-based scenario catalogs for AD evaluation.

Abstract

The increasing complexity of automated driving functions and their growing operational design domains imply more demanding requirements on their validation. Classical methods such as field tests or formal analyses are not sufficient anymore and need to be complemented by simulations. For simulations, the standard approach is scenario-based testing, as opposed to distance-based testing primarily performed in field tests. Currently, the time evolution of specific scenarios is mainly described using trajectories, which limit or at least hamper generalizations towards variations. As an alternative, maneuver-based approaches have been proposed. We shed light on the state of the art and available foundations for this new method through a literature review of early and recent works related to maneuver-based scenario description. It includes related modeling approaches originally developed for other applications. Current limitations and research gaps are identified.

Literature Review on Maneuver-Based Scenario Description for Automated Driving Simulations

TL;DR

The paper addresses the need for robust validation of automated driving systems beyond field tests by exploring maneuver-based scenariodescription for resimulation. It surveys resimulation approaches, maneuver detection/prediction/classification, and trajectory prediction/modeling to assess how high-level maneuvers can enable scalable scenario variation while maintaining consistency with submicroscopic vehicle behavior. A key finding is that maneuver-based resimulation remains rare (only a few studies), highlighting a gap in semantic maneuver sets, trigger mechanisms, and integration with detailed vehicle dynamics. The work argues for combining high-level maneuver descriptions with submicroscopic models and environment-aware triggers to improve realism and transferability in simulation-based safety validation. Overall, the paper maps existing foundations and identifies concrete research directions to advance maneuver-based scenario catalogs for AD evaluation.

Abstract

The increasing complexity of automated driving functions and their growing operational design domains imply more demanding requirements on their validation. Classical methods such as field tests or formal analyses are not sufficient anymore and need to be complemented by simulations. For simulations, the standard approach is scenario-based testing, as opposed to distance-based testing primarily performed in field tests. Currently, the time evolution of specific scenarios is mainly described using trajectories, which limit or at least hamper generalizations towards variations. As an alternative, maneuver-based approaches have been proposed. We shed light on the state of the art and available foundations for this new method through a literature review of early and recent works related to maneuver-based scenario description. It includes related modeling approaches originally developed for other applications. Current limitations and research gaps are identified.
Paper Structure (11 sections, 1 figure, 1 table)

This paper contains 11 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Wording
  3. Literature Review
  4. Resimulation
  5. Trajectory-based approach
  6. Maneuver-based approach
  7. Microscopic and submicroscopic traffic simulation
  8. Maneuver detection, prediction and classification
  9. Trajectory prediction and modeling
  10. Synopsis
  11. Conclusion

Figures (1)

  • Figure 1: Distance- vs. scenario-based testing: scenario-based testing can concentrate on critical situations while long distances of uncritical situations have to be passed before encountering the critical ones in case of distance-based testing