Abstract
Improving safety during interactions between human drivers and automated vehicles requires an environment where autonomous vehicle software can interact with realistic human driving behavior. Generating this behavior has been challenging due to a lack of driver models that accurately reflect both vehicle kinematics and driver cognition. In this project, we propose to develop an active inference model of car-following behavior that will resolve these limitations. The model will be trained using the UC Berkeley INTERACTION dataset. After training, we will work with Waymo to validate the model on an internal dataset and, if necessary, implement a set of augmentations that will allow the model to be used to improve the safety of autonomous vehicle interactions with human drivers.
Project Highlights
Coming Soon!
Final Report
EWD & T2 Products
Coming Soon!
Presentations/Publications
Garcia, A. (2023, September 20). Learning Active Inference Models of Perception and Control. Webinar SafeD Virtual Webinar is available here. PDF of PowerPoint slides from Webinar available here.
Research Investigators (PI*)
Project Information
Start Date: 2022-01-15
End Date: 2023-06-30
Status: Active
Grant Number: 69A3551747115
Total Funding: $150,000
Source Organization: Safe-D National UTC
Project Number: 06-009
Safe-D Theme Areas
Automated Vehicles
Big Data Analytics
Safe-D Application Areas
Driver Factors and Interfaces
Planning for Safety
Vehicle Technology
Performance Measures
Operations and Design
More Information
RiP URL
UTC Project Information Form
Sponsor Organization
Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC 20590 United States
Performing Organization
Texas A&M University
Texas A&M Transportation Institute
3135 TAMU
College Station, Texas 77843-3135
USA