Learning sampling distribution for motion planning with local reconstruction-based self-organizing incremental neural network

Multiobjective path optimization of an indoor AGV based on an improved ACO-DWA

With their intelligence, flexibility, and other characteristics, automated guided vehicles (AGVs) have been popularized and promoted in traditional industrial markets and service industry markets. Compared with traditional transportation methods, AGVs can effectively reduce costs and improve the efficiency of problem solving in various application developments, but they also lead to serious path-planning problems. Especially in large-scale and complex map environments, it is difficult for a single algorithm to plan high-quality moving paths for AGVs, and the algorithm solution efficiency is constrained. This paper focuses on the indoor AGV path-planning problem in large-scale, complex environments and proposes an efficient path-planning algorithm (IACO-DWA) that incorporates the ant colony algorithm (ACO) and dynamic window approach (DWA) to achieve multiobjective path optimization. First, inspired by the biological population level, an improved ant colony algorithm (IACO) is proposed to plan a global path for AGVs that satisfies a shorter path and fewer turns. Then, local optimization is performed between adjacent key nodes by improving and extending the evaluation function of the traditional dynamic window method (IDWA), which further improves path security and smoothness. The results of simulation experiments with two maps of different scales show that the fusion algorithm shortens the path length by 9.9 and 14.1% and reduces the number of turns by 60.0 and 54.8%, respectively, based on ensuring the smoothness and safety of the global path. The advantages of this algorithm are verified. QBot2e is selected as the experimental platform to verify the practicability of the proposed algorithm in indoor AGV path planning.