Miner-Town: Self-Driving Robotics Testbed for Vehicle-To-Grid Simulation
Autonomous vehicles and Vehicle-to-Grid (V2G) technology bring promising implications in boosting energy efficiency, helping the environment, improving our productivity, and have the potential to stabilize the grid during peak times and reduce car accidents. However, implementing and testing these complex novel technologies in the real world comes with high risks and investment. For these reasons, there is the need to research, test, and validate these theories in a compact and controlled environment at minimal cost. This thesis presents a modular autonomous vehicle testbed for the exploration of Vehicle-to-Grid and charging activities in pedestrian filled environments such as a University campus. Previous research on low-cost robotic platforms has reported promising results on control systems, navigation, and object detection; however, the implementation of pedestrian recognition and autonomous docking for V2G chargers remains to be accomplished. By extending the capabilities of existing environments and platforms including Duckietown and the Nvidia Jetbot robot; road following, pedestrian recognition, and autonomous charger docking features are added to enable a Vehicle-to-Grid testbed. Neural networks, supervised learning (classification and regression), and transfer learning techniques are utilized to integrate these functionalities to the testbed. Additionally, the use of fiducial markers is investigated to get a better perception and depth for vehicle to object alignment for camera-based sensing. Through the realized testbed, it is hoped that researchers can understand and overcome the obstacles that these technologies bring with it, to cost effectively learn, develop, and teach the necessary solutions to advance both autonomous vehicles and V2G technology, not only in the classroom, but also to industry.
Cortes Pliego, Carlos Adolfo, "Miner-Town: Self-Driving Robotics Testbed for Vehicle-To-Grid Simulation" (2022). ETD Collection for University of Texas, El Paso. AAI29325852.