Bio-inspired Stochastic Chance-Constrained Multi-Robot Task Allocation Using WSN

The multi-robot task allocation (MRTA) especially in unknown complex environment is one of the fundamental problems, a mostly important object in research of multi-robot. The MRTA problem is initially formulated as a chance-constrained optimization problem. Monte Carlo simulation is used to verify the accuracy of the solution provided by the algorithm. Ant colony optimization (ACO) algorithm based on bionic swarm intelligence was used. A hybrid intelligent algorithm combined Monte Carlo simulation and neural network is used for solving stochastic chance constrained models of MRTA. A practical implementation with real WSN and real mobile robots were carried out. In environment the successful implementation of tasks without collision validates the efficiency, stability and accuracy of the proposed algorithm. The convergence curve shows that as iterative generation grows, the utility increases and finally reaches a stable and optimal value. Results show that using sensor information fusion can greatly improve the efficiency. The algorithm is proved better than tradition algorithms without WSN for MRTA in real time.