Date of Award
5-2023
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Civil Engineering
Committee Chair/Advisor
Dr. Mashrur Chowdhury
Committee Member
Dr. Sakib Mahmud Khan
Committee Member
Dr. Yao Wang
Abstract
Truck platooning can potentially increase the operational efficiency of freight movement on U.S. corridors, improving commercial productivity and economic vibrancy. Predicting each leader vehicle trajectory in the autonomous truck platoon using Artificial Intelligence (AI) can enhance platoon efficiency and safety. Reliance on classical AI may not be efficient for this purpose as it will increase the computational burden for each truck in the platoon. However, Quantum Artificial Intelligence (AI) can be used in this scenario to enhance learning efficiency, learning capacity, and run-time improvements. This study developed and evaluated a Long Short-Term Memory Networks (LSTM) model and a hybrid quantum-classical LSTM (QLSTM) for predicting the trajectory of each leader vehicle of an autonomous truck platoon. Both the LSTM and QLSTM provided comparable results. However, Quantum-AI is more efficient in real-time management for an automated truck platoon as it requires less computational burden. The QLSTM training required less data compared to LSTM. Moreover, QLSTM also used fewer parameters compared to classical LSTM. This study also evaluated an autonomous truck platoon's operational efficacy and string stability with the prediction of trajectory from both classical LSTM and QLSTM using the Intelligent Driver Model (IDM). The platoon operating with LSTM and QLSTM trajectory prediction showed comparable operational efficiency. Moreover, the platoon operating with QLSTM trajectory prediction provided better string stability compared to LSTM.
Recommended Citation
Biswas, Pronab Kumar, "Quantum Artificial Intelligence Supported Autonomous Truck Platooning" (2023). All Theses. 3987.
https://tigerprints.clemson.edu/all_theses/3987