Reptile Honey Badger Optimization Algorithm‐Based Deep Quantum Neural Network for Task Allocation in Multi‐Robot Systems

ABSTRACT Task allocation in multi‐robot systems has been a critical area of research, with applications spanning various industries, such as logistics, agriculture, and manufacturing. The allocation of tasks to multi‐robots improves the system performance, which generally minimizes total resource consumption or cost needed for performing a group of tasks. In dynamic multi‐robot systems, efficient task allocation is critical for optimizing system performance, especially in response to environmental changes like faults or the actions of other robots. Therefore, a new approach called reptile honey badger optimization algorithm_deep quantum neural network (RHBA_DQNN) is framed for task allocation in multi‐robot systems. At first, the tasks are grouped utilizing the fuzzy local information C‐means (FLICM) clustering model. Then, the assignment of tasks for the group of robots is conducted using the devised RHBA, where monetary cost, distance, time, and completion time are considered objective functions. The proposed RHBA is the combination of the reptile search algorithm (RSA) and honey badger algorithm (HBA). Finally, the penalty cost is decided based on the deep quantum neural network (DQNN). Moreover, the RHBA_DQNN has obtained a minimum overall cost, execution time, distance, and monetary cost of 81.251, 9.99, 1.600, and 0.249, respectively.