Robot path planning based on laser range finder and novel objective functions in grey wolf optimizer

Abstract

Mobile robots are the robots that can move through the environment and be used in many applications, including the industrial environment, planet exploration, warehousing, and daily household chores. They can be controlled by an operator, set to do some specific jobs, or work autonomously. Robot path planning is the task of an autonomous robot to move safely from one position to another. In this paper, three new objective functions are introduced in the structure of improved grey wolf optimizer (IGWO) and improved particle swarm optimization (IPSO) for the robot path planning problems. As another part of our proposed method, a reduction of laser range finder (LRF) data is performed, and the avoidance collision approach is also introduced. Robots determine the next position by using LRF data and IGWO (IPSO) algorithms in a local approach. The initial and the goal positions are predefined for each robot. Moreover, the location of static obstacles and other robots are unknown for each robot. Finally, the experimental results of the robot path planning using IGWO are compared to different algorithms. The results indicate that the proposed method performs better in determining an optimal, short, safe, and smooth path. Also, it has less power and time consumption than other methods. All the algorithms are implemented in the V-REP robot simulator.

Neural dynamics based complete grid coverage by single and multiple mobile robots

“…A biologically inspired self-organizing map based methodology was presented in [19] for the application of task assignment of swarm robots. In [20], the authors proposed an improved grey wolf optimizer and particle swarm optimization for mobile robots path planning. Oh et al [21] presented a complete grid coverage algorithm based on the triangular cell decomposition method where the robot was also capable to construct the map of an unknown environment.…”

Design and Development of swarm AGV’s alliance for Search and Rescue operations

“…5) Specific Applications: Some research focuses on specific applications of swarm robotics. For example, [55] discusses self-organized flocking mechanisms for applications like agri-robotics, [53] addresses swarm protection systems for migrants in dangerous territories, and [56] introduces a mobile robot designed for inspecting confined environments. These studies highlight the potential of swarm robotics in addressing specific challenges and offer insights into the design and implementation of specialized systems.…”

A Hybrid Mobile Robot Path Planning Scheme Based on Modified Gray Wolf Optimization and Situation Assessment

“…Since its proposal, the gray wolf optimization (GWO) [10] algorithm has been widely studied because of its advantages of good searching performance, simple structure, and easy implementation. For example, Toufan and Niknafs [11] exploited the cosine function-based searching factors and introduced a dynamic weighting strategy to balance global and local exploring abilities, which improves the solution accuracy of GWO. Olivera et al [12] used an exponential function to attenuate the searching factor α so that the convergence factor is changed nonlinearly and dynamically with the increase of iteration times and tried to find a better trade-off between the search and development stages to ensure that the optimal solution is approached.…”