Project: #564 Low-cost Real-Time Learning-based Localization for Autonomous Vehicles Progress Report - Reporting Period Ending: April 1, 2025 Principal Investigator: Rahul Mangharam Status: Completed Start Date: July 1, 2024 End Date: June 30, 2025 Research Type: None Grant Type: Research Advanced Grant Program: US DOT BIL, Safety21, 2023 - 2028 (4811) Grant Cycle: Safety21 : 24-25 Progress Report (Last Updated: July 31, 2025, 11:07 a.m.) % Project Completed to Date: None % Grant Award Expended: None % Match Expended & Document: None USDOT Requirements Accomplishments This project explores novel approaches to robot localization and visual pose regression using Invertible Neural Networks (INNs). Addressing the critical need for efficient and accurate pose estimation in robotics, we propose two frameworks: Local_INN and PoseINN. Local_INN tackles the inverse problem of robot localization by providing an implicit map representation in its forward path and performing localization in the inverse path. It uniquely offers uncertainty estimation through latent space sampling and addresses the kidnapping problem with a global localization algorithm. PoseINN extends this work to real-time visual-based pose regression from camera data. By leveraging INNs and normalizing flows, PoseINN achieves state-of-the-art performance with significantly reduced computational costs, enabling faster training with low-resolution synthetic data and real-time deployment on mobile robots. Both frameworks demonstrate that INNs can effectively solve ambiguous inverse problems in robotics, providing robust and efficient solutions with inherent uncertainty quantification. Impacts Localization is an important and necessary capability for safety of vehicles. This effort introduces a new approach in using neural networks for localization with invertible neural networks and normalizing flows. This improves the efficiency and accuracy over traditional iterative approaches. Such technology enables lower-cost and more agile autonomous systems. We have incorporated it in the RoboRacer and Autoware autonomous vehicles open-source software stacks for wide dissemination. Other We have incorporated it in the RoboRacer and Autoware autonomous vehicles open-source software stacks for wide dissemination. Outcomes New Partners The Mathworks and Toyota Research Institute has expressed interest in adopting this approach. Issues N/A