Adaptive Parameter Tuning in QRDPSO Using Fuzzy Logic for Enhanced Swarm Robot Navigation

Particle Swarm Optimizer (PSO) is a general optimization tool. It may, however, get stuck in local optima when solving multimodal, non-separable complex problems. PSO is a class of optimization algorithms that model a set of solutions as swarm robots distributed in the search space. In this paper a quantum multi-dimensional moving particle of Robotic Darwinian POS (RDPSO) and quantum potential well model of RDPSO are presented. The parameters for Quantum Robot Darwinian PSO method QRDPSO were then optimized. Experimental results show that the QRDPSO algorithm performs better and is more stable than other optimization algorithms, reaching a global best solution of zero. For regulating robot behavior context-based evaluation metrics are presented in this paper. A fuzzy system with such metrics as input improves Quantum Robot Darwinian PSO parameters. The steady state adaptation of the algorithm permits higher convergence speed, obstacle avoidance agility, and communication limits compliance. An adapted QRDPSO was challenged by mobile robotics simulation evaluation.