Multi-robot task allocation problem with multiple nonlinear criteria using branch and bound and genetic algorithms

Abstract

The paper proposes the formulation of a single-task robot (ST), single-robot task (SR), time-extended assignment (TA), multi-robot task allocation (MRTA) problem with multiple, nonlinear criteria using discrete variables that drastically reduce the computation burden. Obtaining an allocation is addressed by a Branch and Bound (B&B) algorithm in low scale problems and by a genetic algorithm (GA) specifically developed for the proposed formulation in larger scale problems. The GA crossover and mutation strategies design ensure that the descendant allocations of each generation will maintain a certain level of feasibility, reducing greatly the range of possible descendants, and accelerating their convergence to a sub-optimal allocation. The proposed MRTA algorithms are simulated and analyzed in the context of a thermosolar power plant, for which the spatially distributed Direct Normal Irradiance (DNI) is estimated using a heterogeneous fleet composed of both aerial and ground unmanned vehicles. Three optimization criteria are simultaneously considered: distance traveled, time required to complete the task and energetic feasibility. Even though this paper uses a thermosolar power plant as a case study, the proposed algorithms can be applied to any MRTA problem that uses a multi-criteria and nonlinear cost function in an equivalent way. The performance and response of the proposed algorithms are compared for four different scenarios. The results show that the B&B algorithm can find the global optimal solution in a reasonable time for a case with four robots and six tasks. For larger problems, the genetic algorithm approaches the global optimal solution in much less computation time. Moreover, the trade-off between computation time and accuracy can be easily carried out by tuning the parameters of the genetic algorithm according to the available computational power.

Optimization Model of Logistics Task Allocation Based on Genetic Algorithm

“…Li and others analyzed that when manual picking and automatic picking systems are used for partition picking and parallel picking, the manual picking area or unallocated area will affect the picking path of operators and then affect the picking efficiency [9]. Martin and others studied the influence of location allocation on picking efficiency in this type of automatic three-dimensional warehouse with multiple lanes, selected several influencing parameters, i.e., cargo correlation and shipment volume, established the picking time model, and selected heuristic algorithm genetic algorithm to search the optimal solution [10]. Soleimanpour Moghadam and others compared the cost problem of manual picking and automatic picking and took a pharmaceutical distribution center as an example to find the optimal solution by using greedy algorithm [11].…”

Optimization Strategy Analysis of Intelligent Product Service System Based on Computer Simulation Technology

“…Martin et al believe that the modeling of business process-oriented service software and systems not only records the existing service system and determines the requirements of personnel, systems, and facilities but also lays the foundation for the planning and modification, performance evaluation, and optimization of the existing system. In recent years, researchers have been researching and exploring the life cycle of business processes, modeling methods and improvements, and performance evaluation [12]. In the modeling of business processes, Miraglia et al proposed an efficient and formalized process design method; the rules of this process allow the generation of BPMN models integrated with rules from semantic knowledge engineering methods.…”

Task Allocation Using a Team of Robots

“…ere are many types of population-based metaheuristic approaches, including genetic algorithms (e.g. [58,[68][69][70][71][72]), Particle Swarm Optimization (PSO) (e.g. [73,74]), Ant Colony Optimization (ACO) (e.g.…”

“…Branch-and-bound algorithms, and their variants (e.g., [57,58]), provide improved efficiency over exhaustive search techniques, which consider all possible solutions. These algorithms represent all potential solutions as a tree and search branches of the tree, which correspond to subsets of solutions.…”