Computationally Efficient Stochastic Algorithm Supported by Deterministic Technique: A Futuristic Approach

摘要

The challenge of creating a map of the territory solely based on information collected from one or more sensors without any prior knowledge is addressed by simultaneous localization and mapping. Most of the time, a human operator controls the robot, but certain systems can navigate autonomously while mapping; this process is known as active simultaneous localization and mapping. The locomotion mechanism is frequently the primary design consideration for Exploration Robots because of the difficult conditions in which they are typically deployed. Strategies for locomotion that are based on biological systems are frequently advantageous. A common focus is on overall platform design and system integration to build robots that can endure harsh settings long enough to complete their tasks. The aim of the paper is to present the integration of the deterministic method (MAE) with the biologically inspired method for robotic space exploration purposes. The method is called the Multi-Agent Exploration Adaptive Aquila Optimizer (MAE-AAO). The occupancy grid is used as a map for exploration. The algorithms run by first calculating the cost & utility values of all the adjacent surrounding cells of the agent. To increase the rate of exploration, adaptive aquila is used. Upon comparing with other contemporary algorithms, the proposed method outshines in terms of rate of exploration, execution time, and number of aborted simulation runs. The proposed algorithm offers an average of 98% exploration rate with a mean time of only 29 seconds. The method has another distinct feature: zero failed simulation runs, which is the added advantage in the exploration rate.