Abstract
In this study, an effective local minima detection and definition algorithm is introduced for a mobile robot navigating through unknown static environments. Furthermore, five approaches are presented and compared with the popular approach wall-following to pull the robot out of the local minima enclosure namely; Random Virtual Target, Reflected Virtual Target, Global Path Backtracking, Half Path Backtracking, and Local Path Backtracking. The proposed approaches mainly depend on changing the target location temporarily to avoid the original target’s attraction force effect on the robot. Moreover, to avoid getting trapped in the same location, a virtual obstacle is placed to cover the local minima enclosure. To include the most common shapes of deadlock situations, the proposed approaches were evaluated in four different environments; V-shaped, double U-shaped, C-shaped, and cluttered environments. The results reveal that the robot, using any of the proposed approaches, requires fewer steps to reach the destination, ranging from 59 to 73 m on average, as opposed to the wall-following strategy, which requires an average of 732 m. On average, the robot with a constant speed and reflected virtual target approach takes 103 s, whereas the identical robot with a wall-following approach takes 907 s to complete the tasks. Using a fuzzy-speed robot, the duration for the wall-following approach is greatly reduced to 507 s, while the reflected virtual target may only need up to 20% of that time. More results and detailed comparisons are embedded in the subsequent sections.
Highlights
The number of robots deployed in the manufacturing industry has increased drastically in recent times [1]
The results indicate that the Local Path Backtracking approach has the best performance among the five proposed approaches, followed by the Reflected Virtual Target approach
The unit used to measure the efficiency of the proposed methods to address the local minima is the number of steps the robot makes while traveling from the start point to the target point
Summary
The number of robots deployed in the manufacturing industry has increased drastically in recent times [1]. In unmanned aerial vehicle (UAV) applications, commonly known as a drone, cameras play an important role in observing the environment the drone may encounter— in adverse weather events Navigational solutions, such as those proposed in [6,7], rely on the use of automated camera-based systems to improve the navigation and landing of UAVs. in confined spaces, such as in warehouse settings, collaborative robots should consider the presence of humans, objects, and manufacturing machines to avoid any potential accidents in the operational space. Since the robot always follows many steps in the navigation algorithm, it could become stuck in an infinite loop by repeating the steps defined in its algorithm without being able to reach the target destination This local minima issue is referred to in the literature as “limit cycle” [10],” deadlock” [11], “dead end”, “cyclic dead end”, or “trap-situation” [12].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
