Project: #304 Image Processing Approaches to Traffic Situation Understanding, Risk Assessment, and Safety Progress Report - Reporting Period Ending: March 31, 2023 Principal Investigator: Keith Redmill Status: Active Start Date: March 1, 2019 End Date: June 30, 2023 Research Type: Advanced Grant Type: Research Grant Program: FAST Act - Mobility National (2016 - 2022) Grant Cycle: Mobility21 - The Ohio State University Progress Report (Last Updated: April 5, 2023, 11:57 a.m.) % Project Completed to Date: 99 % Grant Award Expended: 99 % Match Expended & Document: 106 USDOT Requirements Accomplishments This project is exploring several potential applications of image processing, including neural network/deep learning technologies, to the analysis of traffic scenes involving passenger and transit vehicles. Topic 1: Investigating the Safety and Robustness of End-to-End Vision-Based Automated Driving Systems Our overall research objective is to integrate planning into vision-based deep reinforcement learning-based automated driving systems. Mapping the image space to the vehicle control space is still an open problem. The more recent end-to-end Deep Reinforcement Learning (DRL) based automated driving algorithms have shown promising results for mapping image pixels to vehicle control signals. However, pure learning-based approaches lack the hard-coded safety measures of model-based counterparts. We propose a hybrid approach for integrating a model-based path planning pipe into a vision-based DRL framework to alleviate the shortcomings of both worlds. We finished the first phase of this topic and published our work in IEEE ITS Society journals. We also open-sourced our code base. The second aspect of our work is investigating deep hierarchical reinforcement learning for end-to-end vision-based automated driving. End-to-end, black-box deep learning models are opaque. For safety-critical applications, interpretability is arguably as important as operational robustness. Against this backdrop, we developed a human-interpretable deep reinforcement learning approach. We are currently leveraging a two-layered hierarchical structure with different temporal resolutions. First, a high-level controller provides long-term interpretable options to the low-level controller. The low-level controller is trained to follow these high-level commands with an intrinsic reward while maintaining operational robustness with an extrinsic reward at a higher frequency. Currently, we are testing this approach in a simulated highway environment and comparing its performance against other state-of-the-art DRL solutions. We developed an object-centric point cloud registration algorithm. We developed this algorithm with a partner from the Technical University of Munich. Our approach is to use object-of-interests to align two different point clouds obtained from two different lidar sensors. With this strategy, we aim to improve point cloud registration performance, which is essential for 3D vision-based driving. We published this work in IEEE Access, an open-access journal. These activities are complete. Topic 2: Extracting Traffic Information from Transit Vehicle Video This project aims to develop an automatic tool for counting traffic flow using a monocular camera. We are using data collected from OSU on-campus bus service, OSU CABS, to analyze traffic flow using the proposed automatic tool. This activity is complete. We have submitted a manuscript for publication in the journal Sensors (MDPI). Topic 3: Optical Flow for Automated Vehicle Control This activity is complete. Additional Activities: We finished the development of the adversarial pedestrian agent to better test our existing driving algorithms. We used deep reinforcement learning to train this adversarial pedestrian agent to test our algorithms more efficiently. We have identified new modes of failure with this analysis, which can impact future research directions. The outcome of this study has been submitted to IEEE Intelligent Vehicles Symposium 2023 and was accepted. We continued our experiments to test our Hierarchical DRL driving agent in the highway simulation environment. We added a new scenario difficulty evaluation metric to assess the high-level decision-making capabilities of driving algorithms. This environment enables us to test high-level decision-making capabilities while evaluating low-level driving actions at the same time. Our preliminary results indicate that the proposed solution learns to make optimal high-level decisions in complex traffic scenarios in a completely end-to-end fashion. We have updated the paper citations. We are preparing the final report for this project. Impacts Topic 1- One journal paper was published. B. L. Žagar, E. Yurtsever, A. Peters, and A. C. Knoll, "Point Cloud Registration With Object-Centric Alignment", IEEE Access, 10(2022), pp. 76586-76595, doi: 10.1109/ACCESS.2022.3191352. Topic 2- The experiments have been completed, and a paper has been submitted to Sensors (MDPI). Other B. L. Žagar, E. Yurtsever, A. Peters, and A. C. Knoll, Point Cloud Registration With Object-Centric Alignment, IEEE Access, 10(2022), pp. 76586-76595. Outcomes New Partners none. Issues None.