This work focuses on developing autonomy-oriented digital twins of vehicles across different scales and configurations to help support the streamlined development and deployment of Autoware Core/Universe stack, using a unified real2sim2real toolchain. Particularly, the core deliverable for this project was to integrate the Autoware stack with AutoDRIVE Ecosystem to demonstrate end-to-end task of mapping an unknown environment, recording a trajectory within the mapped environment, and autonomously tracking the pre-recorded trajectory to achieve the desired objective.
In this video, you can see AutoDRIVE-HunterSE-Autoware integration for autonomous valet parking operational design domain (ODD). Particularly, this AutoDRIVE Simulator demo depicts mapping an unknown structured environment (i.e. Tiny Town) using manual teleoperation, recording a reference trajectory in the mapped environment using manual teleoperation, and then tracking the pre-recorded trajectory autonomously for achieving the end-goal of autonomous valet parking.
AutoDRIVE Ecosystem Website: autodrive-ecosystem.github.io
Paper Preprint: arxiv.org/abs/2402.12670
Technical Report: arxiv.org/abs/2402.14739
AutoDRIVE-Autoware GitHub Repository: github.com/Tinker-Twins/AutoD...
AutoDRIVE-Autoware RU-vid Playlist: • Autoware
10 фев 2024
