Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Validation of Autonomous Vehicles Across Scales using an Integrated Digital Twin Framework

Tanmay Vilas Samak, Chinmay Vilas Samak, Venkat Narayan Krovi

TL;DR

This work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs, and develops a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs).

Abstract

Autonomous vehicle platforms of varying spatial scales are employed within the research and development spectrum based on space, safety and monetary constraints. However, deploying and validating autonomy algorithms across varying operational scales presents challenges due to scale-specific dynamics, sensor integration complexities, computational constraints, regulatory considerations, environmental variability, interaction with other traffic participants and scalability concerns. In such a milieu, this work focuses on developing a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs) to help support the streamlined development and validation of autonomy software stacks. Particularly, this work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs. We study the adoption of these autonomy-oriented digital twins to deploy a common autonomy software stack with an aim of end-to-end map-based navigation to achieve the ODD-specific objective(s) for each vehicle. Finally, we also discuss the flexibility of the proposed framework to support virtual, hybrid as well as physical testing with seamless sim2real transfer.

Towards Validation of Autonomous Vehicles Across Scales using an Integrated Digital Twin Framework

TL;DR

This work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs, and develops a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs).

Abstract

Autonomous vehicle platforms of varying spatial scales are employed within the research and development spectrum based on space, safety and monetary constraints. However, deploying and validating autonomy algorithms across varying operational scales presents challenges due to scale-specific dynamics, sensor integration complexities, computational constraints, regulatory considerations, environmental variability, interaction with other traffic participants and scalability concerns. In such a milieu, this work focuses on developing a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs) to help support the streamlined development and validation of autonomy software stacks. Particularly, this work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs. We study the adoption of these autonomy-oriented digital twins to deploy a common autonomy software stack with an aim of end-to-end map-based navigation to achieve the ODD-specific objective(s) for each vehicle. Finally, we also discuss the flexibility of the proposed framework to support virtual, hybrid as well as physical testing with seamless sim2real transfer.
Paper Structure (24 sections, 5 figures)

This paper contains 24 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Digital Twin Framework
  5. Vehicle Models
  6. Powertrain Dynamics
  7. Brake Dynamics
  8. Steering Dynamics
  9. Suspension Dynamics
  10. Tire Dynamics
  11. Aerodynamics
  12. Sensor Models
  13. Actuator Feedbacks
  14. Incremental Encoders
  15. Inertial Navigation Systems
  16. ...and 9 more sections

Figures (5)

  • Figure 1: Side-by-side comparison of real and virtual autonomous vehicle platforms spanning across various scales and ODDs: Nigel and F1TENTH (small-scale), Husky and Hunter SE (mid-scale), and OpenCAV and RZR (full-scale).
  • Figure 2: Autonomy-oriented vehicle digital twins across scales and ODDs: Nigel (1:14 scale), F1TENTH (1:10 scale), Hunter SE (1:5 scale), and OpenCAV (1:1 scale) platforms for on/off-road autonomy.
  • Figure 3: Calibration and validation of vehicle digital twins: (a) System identification of Nigel, (b) VESC calibration of F1TENTH, (c) Static measurements of Hunter SE, and (d) Powertrain measurements of OpenCAV.
  • Figure 4: Virtual proving ground environments across different scales and ODDs. Small-scale environments are typically synthetic while mid-scale and full-scale environments can be synthetic as well as realistic.
  • Figure 5: Validation of the integrated operation of AutoDRIVE Ecosystem in conjunction with Autoware stack for end-to-end map-based navigation case studies tailored to the unique requirements of each vehicle's scale and ODD. Videos: https://youtube.com/playlist?list=PL5Hd4DIMOmEJgpsPYCoLBGNb_91PZVxgA&si=w2wO9h2xKm_IrA1f