Abstract
Based on automated guided vehicle (AGV), the intelligent parking system provides a novel solution to the difficulty of parking in large cities. The automation of parking/pick-up in the system hinges on the path planning efficiency of the AGV. Considering the numerous disconnected paths in intelligent parking systems, this paper introduces the fallback strategy to improve ant colony optimization (ACO) for path planning in AGV-based intelligent parking system. Meanwhile, the valuation function was adopted to optimize the calculation process of the heuristic information, and the reward/penalty mechanism was employed to the pheromone update strategy. In this way, the improved ACO could plan the optimal path for the AGV from the starting point to the destination, without sacrificing the search efficiency. Next, the optimal combination of ACO parameters was identified through repeated simulations. Finally, a typical parking lot was abstracted into a topological map, and used to compare the path planning results between the improved ACO and the classic ACO. The comparison confirms the effectiveness of the improved ACO in path planning for AGV-based intelligent parking system.
Highlights
The rapid growth of car ownership adds to the difficulty of parking in large cities, where parking spaces are already very limited
The path planning for intelligent parking system was realized in three steps: Firstly, the driving rules of the automated guided vehicle (AGV) in intelligent parking system were analyzed, and the constraints of the path planning model were put forward; the environment of parking lot was modelled as a topological map, and the basic requirements were raised for environmental modelling, facilitating the subsequent analysis of data; the improved ant colony optimization (ACO) based on the fallback strategy was established according to the features of intelligent parking system
The constraints of path planning were determined according to the operation features of the intelligent parking system, and the driving rules for the AGV in the parking lot
Summary
The rapid growth of car ownership adds to the difficulty of parking in large cities, where parking spaces are already very limited. Based on vehicle scheduling model, Nishi et al [16] presented a bi-level decomposition algorithm, which realizes conflict-free path planning for multiple AGVs. Based on the above research results, it can be found that most of the current path planning algorithms for intelligent parking systems are mainly focused on solving collision avoidance conflicts and realizing multi-vehicle scheduling, and rarely involve the improvement of path planning efficiency. In order to improve the operation efficiency of small-scale intelligent parking systems, this research put forward the improved ACO model for single AGV path planning. The characteristics of incomplete path connectivity in AGV-based intelligent parking systems seriously restrict the path search efficiency of classical ant colony algorithm. To prevent the ACO from the local optimum trap and poor convergence, the valuation function was adopted to optimize the calculation process of the heuristic information, and the reward/penalty mechanism was employed to the pheromone update strategy, ensuring the search efficiency. The remainder of this paper is organized as follows: Section 2 proposes the path planning model for intelligent parking system based on the improved ACO, in the light of the features of intelligent parking system; Section 3 verifies the improved ACO through example analysis, in comparison with the classic ACO; Section 4 puts forward the research conclusions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
