TY - JOUR
T1 - Synchromodal freight transport re-planning under service time uncertainty
T2 - An online model-assisted reinforcement learning
AU - Zhang, Yimeng
AU - Negenborn, Rudy R.
AU - Atasoy, Bilge
PY - 2023
Y1 - 2023
N2 - The objective of this study is to address the issue of service time uncertainty in synchromodal freight transport, which can cause delays, inefficiencies, and reduced satisfaction for shippers. The proposed solution is an online deep Reinforcement Learning (RL) approach that takes into account the service time uncertainty, assisted by an Adaptive Large Neighborhood Search (ALNS) heuristic that provides state and reward information based on the routing and scheduling. The proposed planning approach re-plans in response to unexpected events and learns from real-time information from various transport modes, including road, railway, and inland waterways. The performance of the proposed planning approach is evaluated in the European Rhine-Alpine corridor under various scenarios with different types and severities of unexpected events. The results demonstrate that the RL approach consistently outperforms other strategies by effectively handling service time uncertainty, leading to reduced costs, emissions, and waiting time, as well as decreased transport delays and improved rewards through accurate decision-making and agile transport re-planning. This study also finds that incorporating event severity information improves the average reward obtained by the RL approach in scenarios involving multiple types of events.
AB - The objective of this study is to address the issue of service time uncertainty in synchromodal freight transport, which can cause delays, inefficiencies, and reduced satisfaction for shippers. The proposed solution is an online deep Reinforcement Learning (RL) approach that takes into account the service time uncertainty, assisted by an Adaptive Large Neighborhood Search (ALNS) heuristic that provides state and reward information based on the routing and scheduling. The proposed planning approach re-plans in response to unexpected events and learns from real-time information from various transport modes, including road, railway, and inland waterways. The performance of the proposed planning approach is evaluated in the European Rhine-Alpine corridor under various scenarios with different types and severities of unexpected events. The results demonstrate that the RL approach consistently outperforms other strategies by effectively handling service time uncertainty, leading to reduced costs, emissions, and waiting time, as well as decreased transport delays and improved rewards through accurate decision-making and agile transport re-planning. This study also finds that incorporating event severity information improves the average reward obtained by the RL approach in scenarios involving multiple types of events.
KW - Deep reinforcement learning
KW - Online transport planning
KW - Service time
KW - Synchromodal transport
KW - Uncertainty
UR - http://www.scopus.com/inward/record.url?scp=85172385529&partnerID=8YFLogxK
U2 - 10.1016/j.trc.2023.104355
DO - 10.1016/j.trc.2023.104355
M3 - Article
AN - SCOPUS:85172385529
SN - 0968-090X
VL - 156
JO - Transportation Research Part C: Emerging Technologies
JF - Transportation Research Part C: Emerging Technologies
M1 - 104355
ER -