Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Sim2Real Transfer of Autonomy Algorithms using AutoDRIVE Ecosystem

Chinmay Vilas Samak, Tanmay Vilas Samak, Venkat Krovi

TL;DR

This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem.

Abstract

The engineering community currently encounters significant challenges in the development of intelligent transportation algorithms that can be transferred from simulation to reality with minimal effort. This can be achieved by robustifying the algorithms using domain adaptation methods and/or by adopting cutting-edge tools that help support this objective seamlessly. This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem. In this paper, we extensively explore the modeling and simulation aspects of the ecosystem and substantiate its efficacy by demonstrating the successful transition of two candidate autonomy algorithms from simulation to reality to help support our claims: (i) autonomous parking using probabilistic robotics approach; (ii) behavioral cloning using deep imitation learning. The outcomes of these case studies further strengthen the credibility of AutoDRIVE as an invaluable tool for advancing the state-of-the-art in autonomous driving technology.

Towards Sim2Real Transfer of Autonomy Algorithms using AutoDRIVE Ecosystem

TL;DR

This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem.

Abstract

The engineering community currently encounters significant challenges in the development of intelligent transportation algorithms that can be transferred from simulation to reality with minimal effort. This can be achieved by robustifying the algorithms using domain adaptation methods and/or by adopting cutting-edge tools that help support this objective seamlessly. This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem. In this paper, we extensively explore the modeling and simulation aspects of the ecosystem and substantiate its efficacy by demonstrating the successful transition of two candidate autonomy algorithms from simulation to reality to help support our claims: (i) autonomous parking using probabilistic robotics approach; (ii) behavioral cloning using deep imitation learning. The outcomes of these case studies further strengthen the credibility of AutoDRIVE as an invaluable tool for advancing the state-of-the-art in autonomous driving technology.
Paper Structure (28 sections, 7 figures)

This paper contains 28 sections, 7 figures.

Table of Contents

  1. Introduction
  2. State of the Art
  3. Software Simulators
  4. Hardware Testbeds
  5. AutoDRIVE Ecosystem
  6. Physical Vehicle
  7. Chassis
  8. Power Electronics
  9. Sensor Suite
  10. Computation, Communication and Software
  11. Actuators
  12. Lights and Indicators
  13. Virtual Vehicle
  14. Suspension Dynamics
  15. Wheel Dynamics
  16. ...and 13 more sections

Figures (7)

  • Figure 1: AutoDRIVE Ecosystem offers of a tightly integrated trio for designing, simulating and deploying autonomy solutions using a unified workflow.
  • Figure 2: Native vehicle (Nigel) of AutoDRIVE Ecosystem with its components and sub-systems highlighted.
  • Figure 3: Simulation of vehicle dynamics, sensors and actuators. The left inset depicts actuator dynamics model and the right inset depicts tire dynamics model.
  • Figure 4: Infrastructure setup in simulation and reality. Note the degree of dimensional and visual similarity between real and virtual worlds.
  • Figure 5: Architectures of the two presented case-studies.
  • ...and 2 more figures