Bridging the Sim-to-Real Gap in Motion Planning for Autonomous Electric Vehicles Using Autoware: A Comparative Study of Simulation and Real-World Deployment
Road traffic accidents result in over 1.35 million fatalities annually, highlighting the urgent need for safer transportation systems. Autonomous Electric Vehicles (AEVs), powered by advancements in Intelligent Transportation Systems (ITS), offer a promising solution by enhancing road safety and eff...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11077125/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Road traffic accidents result in over 1.35 million fatalities annually, highlighting the urgent need for safer transportation systems. Autonomous Electric Vehicles (AEVs), powered by advancements in Intelligent Transportation Systems (ITS), offer a promising solution by enhancing road safety and efficiency. This study focuses on trajectory planning for AEVs, a critical component for safe navigation in dynamic environments. Using Autoware.ai, an open-source modular platform, a novel interface integrating custom point cloud (PCD) and vector maps for precise localization and navigation was developed. The proposed method was tested in both simulation and real-world scenarios on the SRM IST campus, addressing challenges such as the “sim-to-real gap” caused by discrepancies between simulated and real-world conditions. Quantitative analysis of planned, simulated, and measured trajectories revealed significant improvements in localization accuracy and trajectory adherence, with Root Mean Square Error (RMSE) values for longitudinal and lateral positions reduced to 0.839 m and 0.1044 m, respectively. Velocity and steering angle tracking demonstrated minor deviations due to actuator constraints and road conditions. This research provides valuable insights into bridging the sim-to-real gap in AEV trajectory planning, paving the way for safer and more reliable autonomous driving systems. |
|---|---|
| ISSN: | 2169-3536 |