Adaptive Cost Coefficient Identification for Planning Optimal Operation in Mobile Robot based Internal Transportation
For autonomous logistic systems, this provides a method to improve route planning efficiency by adapting to real-time travel costs.
This work identifies cost coefficients for travel times in multi-robot internal transportation systems using Kalman filtering, achieving a 15% average reduction in total traversing cost.
Decisions in automated logistic systems can be improved based on knowledge of real-time state of individual parts and also environmental factors. These knowledge can be obtained through travel time of edges by individual robots which represents the utility based costs in the system. Our work focuses on identifying \textbf{cost coefficients} in an autonomous multi-robot system used for internal transportation. With suitable predictions of these travel times the current status of cost involved in traversing from one node to another can be known. Thus suitable state-space model is formulated and Kalman filtering is used to estimate these travel time to use as weights for cost efficient route planning. Experiments show that paths obtained using online \textbf{travel times} as weights have total traversing cost reduces by 15\% on average.