Quantum Artificial Intelligence-Supported Trajectory Prediction for an Autonomous Truck Platoon

Details

• Creators:
  Biswas, Pronab Kumar ; Salek, M Sabbir ; Chowdhury, Mashrur ; Comert, Gurcan ; Michalaka, Dimitra ; Mwakalonge, Judith L. ; Huynh, Nathan ; Charles, Frank ; Ahmed, Fahim ; Tine, Jean Michel
• Corporate Creators:
  Center for Connected Multimodal Mobility, Clemson University ; Benedict College ; Citadel, the Military College of South Carolina ; South Carolina State University ; University of Nebraska-Lincoln
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  • Artificial intelligence
  • Autonomous vehicles
  • Drivers
  • Traffic platooning
  • Trajectory
  • Hybrid automobiles
  • Predictive models
  • Quantum Artificial Intelligence
  • Autonomous Truck
  • Driver Model
  More +
• Publication/ Report Number:
  Final Report (2021 - 2024)
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report (2021 - 2024)
• Corporate Publisher:
  Center for Connected Multimodal Mobility, Clemson University
• Abstract:
  Truck platooning can potentially increase the operational efficiency of freight movement on U.S. corridors, improving commercial productivity and economic vibrancy. Predicting the trajectory of each leading vehicle in an autonomous truck platoon using Artificial Intelligence (AI) can enhance platoon efficiency during unavailability of the real-time trajectory information, which could occur due to different reasons, such as data loss, delay in communications, and noisy and erroneous sensor measurements. This study developed and evaluated a Long Short-Term Memory (LSTM) model and a hybrid quantum-classical LSTM (QLSTM) model for predicting the trajectory of each leading truck in an autonomous truck platoon. Both the LSTM and QLSTM showed potential to be utilized to predict trajectories for platoon management. However, the QLSTM models performed better in predicting trajectories than the LSTM models. The QLSTM-based predictions yielded higher operational benefits than the LSTM-based predictions. Moreover, the QLSTM used fewer parameters for training, which would require less memory compared to classical LSTM.
• Format:
  PDF
• Funding:
  69A3551747117
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/80354/dot_80354_DS1.pdf
• File Type:
  [PDF - 1.17 MB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; Autonomous Vehicles ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:fbe3cae719f88f047267bb7bd3f005a5833c0f151fa793df91e1987b9ee37f62ea3644679fc4fda993638448807d30803a8aff0b5f0a3597c90198538ce87cc1