Autonomous vehicle path planning for smart logistics mobile applications based on modified heuristic algorithm

Abstract

In this research, a heuristic algorithm is used to find an optimal route for smart logistic loading and unloading operations. Various environments, such as traditional building blocks, satellite images, terrain environments, and Google map environments are used to optimize the viable path in the smart mobile logistic application. The proposed autonomous vehicle route planning navigation approach is to forecast the autonomous vehicle's path until it detects an imminent obstacle, at which point it should turn to the safest area before continuing on its route. The algorithm can identify the best route between two locations in the target space by taking into account of various aspects including obstacle violation, detection probability, convergence rate, and path length. To demonstrate the path navigation results of proposed algorithms, a navigational model is developed in the MATLAB/Simulink 2D virtual environment. To find the most feasible path for a given application environment, the particle swarm optimization method, the Bat search algorithm, and its variants are presented. According to extensive simulation and benchmark validation results, the proposed Standard particle swarm optimization (SPSO) has a significantly shorter path, quick convergence rate and take less time to compute the distance between the loading and unloading environment locations than the Bat search algorithm and its variants.

Self-adaptive learning particle swarm optimization-based path planning of mobile robot using 2D Lidar environment

“…LPSO retains the fundamental components of PSO, including the concept of particles, their positions, velocities, and the social learning process. Each particle in the swarm maintains its position and velocity, updates them based on its own experience, and communicates with neighboring particles to share information about the best solutions found, Velocity Particle Swarm Optimization (VPSO) implemented by Fusic, S. Julius [29, 30] stated the primary distinction of VPSO is its central focus on controlling and optimizing particle velocities. The adjustment of velocities helps particles navigate through the search space effectively, allowing them to escape local optima and converge toward global optima, and Binary Particle Swarm Optimization (BPSO) tailored for discrete optimization problems where variables can take binary values, typically 0 or 1 [31, 32].…”

Research on mobile robot path planning in complex environment based on DRQN algorithm

“…The motion model of the mobile robot developed in this section is shown in figure 1. Its differential equation of lateral dynamics is shown in equation (1).…”

“…With the rapid development of artificial intelligence technology, the environment-sensing ability and the degree of unmanned autonomous control of mobile robots are constantly being improved [1]. Technological research in unmanned aerial vehicles (UAV) and unmanned surface vehicles (USV) are more mature [2], and have been widely used in terrain reconnaissance [3] and underwater exploration [4] missions in different environments.…”

A novel path generation method for robotic measurement with local pruning and collision-free adjustment

“…Mukadam et al [20] used the Gaussian processes to replace the discrete state in many practical scenarios and optimized the objective function by gradient descent to obtain the optimal trajectory. Fusic et al [21] uses a combination of several optimization algorithms to try to find smooth paths. The optimization-based method usually requires establishing an objective function and selecting an appropriate iterative optimization algorithm, which not only results in algorithmic complexity, but also makes the solution process is very time-consuming.…”