Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Digital Twin prototype for traffic sign recognition of a learning-enabled autonomous vehicle

Mohamed AbdElSalam, Loai Ali, Saddek Bensalem, Weicheng He, Panagiotis Katsaros, Nikolaos Kekatos, Doron Peled, Anastasios Temperekidis, Changshun Wu

TL;DR

A novel digital twin prototype for a learning-enabled self-driving vehicle that relies on co-simulation and uses the Functional Mock-up Interface and SystemC Transaction Level Modeling standards to perform traffic sign recognition and lane keeping.

Abstract

In this paper, we present a novel digital twin prototype for a learning-enabled self-driving vehicle. The primary objective of this digital twin is to perform traffic sign recognition and lane keeping. The digital twin architecture relies on co-simulation and uses the Functional Mock-up Interface and SystemC Transaction Level Modeling standards. The digital twin consists of four clients, i) a vehicle model that is designed in Amesim tool, ii) an environment model developed in Prescan, iii) a lane-keeping controller designed in Robot Operating System, and iv) a perception and speed control module developed in the formal modeling language of BIP (Behavior, Interaction, Priority). These clients interface with the digital twin platform, PAVE360-Veloce System Interconnect (PAVE360-VSI). PAVE360-VSI acts as the co-simulation orchestrator and is responsible for synchronization, interconnection, and data exchange through a server. The server establishes connections among the different clients and also ensures adherence to the Ethernet protocol. We conclude with illustrative digital twin simulations and recommendations for future work.

A Digital Twin prototype for traffic sign recognition of a learning-enabled autonomous vehicle

TL;DR

A novel digital twin prototype for a learning-enabled self-driving vehicle that relies on co-simulation and uses the Functional Mock-up Interface and SystemC Transaction Level Modeling standards to perform traffic sign recognition and lane keeping.

Abstract

In this paper, we present a novel digital twin prototype for a learning-enabled self-driving vehicle. The primary objective of this digital twin is to perform traffic sign recognition and lane keeping. The digital twin architecture relies on co-simulation and uses the Functional Mock-up Interface and SystemC Transaction Level Modeling standards. The digital twin consists of four clients, i) a vehicle model that is designed in Amesim tool, ii) an environment model developed in Prescan, iii) a lane-keeping controller designed in Robot Operating System, and iv) a perception and speed control module developed in the formal modeling language of BIP (Behavior, Interaction, Priority). These clients interface with the digital twin platform, PAVE360-Veloce System Interconnect (PAVE360-VSI). PAVE360-VSI acts as the co-simulation orchestrator and is responsible for synchronization, interconnection, and data exchange through a server. The server establishes connections among the different clients and also ensures adherence to the Ethernet protocol. We conclude with illustrative digital twin simulations and recommendations for future work.
Paper Structure (15 sections, 10 figures)

This paper contains 15 sections, 10 figures.

Table of Contents

  1. Introduction
  2. Key enabling technologies for Digital Twins
  3. Co-simulation.
  4. Functional Mock-up Interface (FMI).
  5. Transaction Level Modeling (TLM).
  6. Behavior, Interaction, Priority (BIP).
  7. Digital Twin platform.
  8. Developing a Digital Twin for traffic sign recognition and lane keeping
  9. Vehicle model: Amesim
  10. Steering control: ROS
  11. Environment model: Prescan
  12. Perception and speed control module: BIP
  13. Orchestration: PAVE360-VSI platform
  14. Digital Twin simulation
  15. Conclusion

Figures (10)

  • Figure 1: Digital twin prototype for traffic sign recognition of a learning-enabled vehicle. Architecture: PAVE360-VSI DT platform containing a server and four clients/components; a vehicle model modeled in AMESIM, a control ROS subsystem, a control module modeled in BIP, and a Prescan model. All tools are co-simulated and interconnected via gateways.
  • Figure 2: Vehicle Model in Amesim; the left part shows the inputs and outputs of the FMU client, while the right part displays a visual representation of the Simrod Amesim FMU.
  • Figure 3: Digital Twin component - ROS client - steering control module.
  • Figure 4: Digital Twin component - Prescan scenario - environment model and driving track.
  • Figure 5: Digital Twin component - BIP module - speed control regulation and perception with YOLOX.
  • ...and 5 more figures