Static and dynamic path optimization of multiple mobile robot using hybridized fuzzy logic-whale optimization algorithm

Kumar, Saroj; Parhi, Dayal R.; Kashyap, Abhishek; Muni, Manoj Kumar

doi:10.1177/0954406220982641

Cited by 22 publications

(15 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robot's speed is limited to 0.8 m per second, and the simulation environment scale is 0.5 m/unit and the screen size is 20 by 20. The target point is (19,7). The weight matrices of the cost function are considered Q = 100I and R = 5I and θ sc ¼ π 8 .…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

“…1 However, keeping abreast of developing computational tools, the foregoing subject has gradually stimulated the interest of many researchers in the field of mobile robot navigation. [2][3][4][5] Referring to the literature, several scenarios have been proposed for robotic navigation, [6][7][8] which falls into two categories, namely classical and reactive. 4 The Potential Field (PF) 9 and Rapidly exploring Random Tree (RRT), 10 bug, 11,12 and velocity obstacle 13 methods are among the classical approaches.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The synergy of the multi-modal MPC and Q-learning approach for the navigation of a three-wheeled omnidirectional robot based on the dynamic model with obstacle collision avoidance purposes

Saeedinia

Masouleh

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

This paper proposes a new navigation control scheme for a three-wheel OMnidirectional Robot (OMR), taking into account the dynamic constraints with the aim of collision avoidance in dynamic environments. The proposed control strategy is inherently a multi-modal adaptive-Reinforcing model-based controller (MAR-MPC), which can be regarded as a judicious synergy of multi-modal MPC (MMPC) and Q-Learning (QL) to optimal navigation. This method takes advantage of a larger convergence area, compared to MMPC and MPC, and presents near-optimal MPC performance. The navigation scheme utilizes an online stochastic observer, namely, a Kalman filter, to estimate the future state of the robot. This paper formulates a general collision avoidance navigation problem in a constrained linear convex cone structure to make it real-time implementable. Furthermore, the proposed multi-modal path planning algorithm reduces the required prediction horizon and consequently affects computational cost. To evaluate the performance of the proposed navigation strategy, two static and two dynamic environment instances are simulated, and the results are compared with four algorithms, namely, Exploring Random Tree (RRT), Potential Field (PF), MPC, and MMPC. Results indicate the superior performance of the proposed navigation method in aspects of time and distance costs and collision avoidance criterion. Moreover, the proposed algorithm provides the feasibility and stability guarantee and a larger convergence region.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The synergy of the multi-modal MPC and Q-learning approach for the navigation of a three-wheeled omnidirectional robot based on the dynamic model with obstacle collision avoidance purposes

Saeedinia

Masouleh

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

show abstract

“…8 In recent years, scholars pay more attention to improve efficiency and reliability of A* algorithm for WMRs. 9 For example, in order to solve specific scenario problems, aiming at inflexible directions, Liu 10 extended the space dimension by adding heading angle, vehicle forward and rear motion information, hence increased the selection nodes of veering which directly improved the efficiency of path planning. However, the obstacle avoidance was not taken into consideration and the heading angle error was limited to adjacent nodes which probably leads to unsuccessful planning for complex terrain.…”

Section: Introductionmentioning

confidence: 99%

An improved target-oriented path planning algorithm for wheeled mobile robots

Yao

Yue

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

This paper proposes a target posture-oriented path planning method, where an improved A* algorithm and an optimized dynamic windows approach (DWA) are used at the global and local planning aspects, respectively. The method enables wheeled mobile robots (WMRs) to plan an optimal path under different posture situations which can shorten the time of achieving navigation task in certain scene. On the hand of global path planning, target posture and orientation information are added into A* algorithm to obtain appropriate path. At the level of local path planning, based on DWA, evaluation functions are optimized to make the robot movement adapting to curve global path and dynamic obstacle. By introducing rotation index to evaluate experiment results, the tests verify that WMRs can reasonably plan more efficient path compared with traditional path planning method, by satisfying various posture demand with the aid of the proposed target posture-oriented A* algorithm, and quickly avoid dynamic obstacles via the optimized DWA. Therefore, the proposed algorithm can be effectively applied to WMRs to execute various target posture demands navigation tasks.

show abstract

“…Castillo et al 53 have presented path optimization for mobile robots using GA. Pandey et al 54,55 have proposed a V-REP-based analysis of navigational control for mobile robots using PSO-tuned FNN and ANFIS controller in two different scenarios. Kumar et al 56 have poposed a hybridized technique for navigational control over multiple mobile robots. Muni et al 57 have explained prim's algorithm for path optimization of humanoid robots.…”

Section: Introductionmentioning

confidence: 99%

Hybrid IWD-GA: An Approach for Path Optimization and Control of Multiple Mobile Robot in Obscure Static and Dynamic Environments

et al. 2021

Self Cite

View full text Add to dashboard Cite

SUMMARY In this article, hybridization of IWD (intelligent water drop) and GA (genetic algorithm) technique is developed and executed in order to obtain global optimal path by replacing local optimal points. Sensors of mobile robots are used for mapping and detecting the environment and obstacles present. The developed technique is tested in MATLAB simulation platform, and experimental analysis is performed in real-time environments to observe the effectiveness of IWD-GA technique. Furthermore, statistical analysis of obtained results is also performed for testing their linearity and normality. A significant improvement of about 13.14% in terms of path length is reported when the proposed technique is tested against other existing techniques.

show abstract

Static and dynamic path optimization of multiple mobile robot using hybridized fuzzy logic-whale optimization algorithm

Cited by 22 publications

References 42 publications

The synergy of the multi-modal MPC and Q-learning approach for the navigation of a three-wheeled omnidirectional robot based on the dynamic model with obstacle collision avoidance purposes

The synergy of the multi-modal MPC and Q-learning approach for the navigation of a three-wheeled omnidirectional robot based on the dynamic model with obstacle collision avoidance purposes

An improved target-oriented path planning algorithm for wheeled mobile robots

Hybrid IWD-GA: An Approach for Path Optimization and Control of Multiple Mobile Robot in Obscure Static and Dynamic Environments

Contact Info

Product

Resources

About