Search

Purpose: Smooth and autonomous navigation of mobile robot in a cluttered environment is the main purpose of proposed technique. That includes localization and path planning of mobile robot. These are important aspects of the mobile robot during autonomous navigation in any workspace. Navigation of mobile robots includes reaching the target from the start point by avoiding obstacles in a static or dynamic environment. Several techniques have already been proposed by the researchers concerning navigational problems of the mobile robot still no one confirms the navigating path is optimal. Design/methodology/approach: Therefore, the modified grey wolf optimization (GWO) controller is designed for autonomous navigation, which is one of the intelligent techniques for autonomous navigation of wheeled mobile robot (WMR). GWO is a nature-inspired algorithm, which mainly mimics the social hierarchy and hunting behavior of wolf in nature. It is modified to define the optimal positions and better control over the robot. The motion from the source to target in the highly cluttered environment by negotiating obstacles. The controller is authenticated by the approach of V-REP simulation software platform coupled with real-time experiment in the laboratory by using Khepera-III robot. Findings: During experiments, it is observed that the proposed technique is much efficient in motion control and path planning as the robot reaches its target position without any collision during its movement. Further the simulation through V-REP and real-time experimental results are recorded and compared against each corresponding results, and it can be seen that the results have good agreement as the deviation in the results is approximately 5% which is an acceptable range of deviation in motion planning. Both the results such as path length and time taken to reach the target is recorded and shown in respective tables. Originality/value: After literature survey, it may be said that most of the approach is implemented on either mathematical convergence or in mobile robot, but real-time experimental authentication is not obtained. With a lack of clear evidence regarding use of MGWO (modified grey wolf optimization) controller for navigation of mobile robots in both the environment, such as in simulation platform and real-time experimental platforms, this work would serve as a guiding link for use of similar approaches in other forms of robots.

Purpose: This study aims to modify a nature-based numerical method named the invasive weed optimization (IWO) method for mobile robot path planning in various complex environments. Design/methodology/approach: The existing IWO method is quick in converging to a feasible solution but in a complex environment; it takes more time as well as computational resources. So, in this paper, the computational part of this artificial intelligence technique is modified with the help of recently developed evolution algorithms like particle swarm optimization, genetic algorithm, etc. Some conditional logic statements were used while doing sensor-based mapping for exploring complex paths. Implementation of sensor-based exploration, mathematical IWO method and prioritizing them for better efficiency made this modified IWO method take complex dynamic decisions. Findings: The proposed modified IWO is better for dynamic obstacle avoidance and navigating a long complex map. The deviation of results in simulation and experiments is less than 5.5%, which validates a good agreement between simulation and real-time testing platforms. Originality/value: As per a deep literature review, it has found that the proposed approach has not been implemented on the Khepera-III robot for smooth motion planning. Here a dynamic obstacle mapping feature is implemented. A method to selectively distribute seeds instead of a random normal distribution is also implemented in this work. The modified version of IWO is coded in MATLAB and simulated through V-Rep simulation software. The integration of sensors was done through logical conditioning. The simulation results are validated using real-time experiments.