Proposed end-to-end multi-task model (IMAGE) Toyohashi University of Technology (TUT) Caption The AI model architecture is composed of the perception module (blue) and the controller module (green). The perception module is responsible for perceiving the environment based on the observation data provided by an RGBD camera. Meanwhile, the controller module is responsible for decoding the extracted information to estimate the degree of steering, throttle, and braking. Credit COPYRIGHT (C) TOYOHASHI UNIVERSITY OF TECHNOLOGY. ALL RIGHTS RESERVED. Usage Restrictions None License Original content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.