Research on Path Planning of Automated Parking Robots Based on Improved RRT Algorithm

DOI: https://doi.org/10.62517/jbdc.202601103

Author(s)

Zichuan Wang1, Yawen Fan2,*, Jingfeng Shen1,*, Shikun Zhang1, Fangting Liu1

Affiliation(s)

1School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China 2Sino-British International College, University of Shanghai for Science and Technology, Shanghai, China *Corresponding Author

Abstract

This paper proposed an improved RRT path planning algorithm based on child reconnection (RRT with Child Reconnection, RRT-CRe). It addresses the limitations of the basic Rapidly Expanding Random Tree (RRT) algorithm in narrow, compact environments like smart garages, where it suffers from blind expansion and low sampling point utilization during parking path planning. A realistic three-dimensional environment model was first formulated for a selected intelligent garage zone under weekday peak-hour conditions, enabling accurate representation of real-time occupancy. Building upon this environment, a goal-biased sampling and expansion strategy enhanced by a child-reconnection mechanism was proposed to overcome the inefficiency of conventional RRT. To further ensure feasibility under practical constraints, a circumscribed-circle model was integrated into the local rewiring phase, capturing the geometric limitations of automated parking robots and their surroundings. Results show that in narrow and complex environments involving multiple target points, the proposed RRT-CRe algorithm substantially outperforms the basic RRT, achieving an average reduction of approximately 55% in parking time and an improvement of about 45% in success rate. Moreover, when compared with RRT*, a widely used derivative of the basic RRT, RRT-CRe still exhibits an increase of approximately 35% in success rate. These results collectively demonstrate that the proposed algorithm satisfies the efficiency and reliability requirements of automated parking robots in challenging scenarios.

Keywords

RRT; Path Planning; Intelligent Garage; Automated Parking Robot

References

[1] Wang L, Zhu X, Li Z, et al. Ultrasonic Obstacle Avoidance and Full-Speed-Range Hybrid Control for Intelligent Garages. Sensors, 2024, 24(17):5694-5696. [2] Jiang N, Han Y. Patent technology development of intelligent stereo garage. China Science and Technology Information, 2024, (14): 31–33. [3] Neeru M, Mamta M, Jude D H, et al. Deep learning and saliency-based parking IoT classification under different weather conditions. Intelligent Decision Technologies, 2024, 18(2):1411-1424. [4] Venkata S, Sai M, Yaswanth T, et al. Smart garage utilizing Internet of Things (IoT). Journal of Sensors, 2022, 1156(22): 255-265. [5] Ren Z, Cai A, Xu F. Automated guided vehicle (AGV) path optimization method based on improved rapidly-exploring random trees. Computer Science, 2025, 11: 15-24. [6] Zhao X, Wang K, Zhang P, et al. An improved RRT* path planning algorithm combining Gaussian distributed sampling and depth strategy for robotic arm of fruit-picking robot. Computers and Electronics in Agriculture, 2025, 207: 111244. [7] Venu S, Gurusamy M. A comprehensive review of path planning algorithms for autonomous navigation. Results in Engineering, 2025, 28: 107750. [8] Jeong I, Lee S, Kim J. Quick-RRT*: Triangular Inequality-based Implementation of RRT* with Improved Initial Solution and Convergence Rate. Expert Systems with Applications, 2019, 123:82-90. [9] Bin L, Yi H, Fang W, et al. Stack-RRT*: A Random Tree Expansion Algorithm for Smooth Path Planning. International Journal of Control, Automation and Systems, 2023, 21(3): 993-1004. [10]Wang H, Zhou X, Li J, et al. Improved RRT* algorithm for disinfecting robot path planning. Sensors, 2024, 24(5): 1417. [11] Jun D, Yin Z, Xia H, et al. An improved RRT* algorithm for robot path planning based on path expansion heuristic sampling. Journal of Computational Science, 2023, 67: 102085. [12]Wu Z, Dai J, Jiang B, et al. Robot path planning based on artificial potential field with deterministic annealing. ISA Transactions, 2023, 138:74–87. [13]Yang Z, Hu J, Zhao H. AMP-RRT*: an adaptive multi-layer path planning algorithm for robots in complex environments. Engineering Research Express, 2025, 7(3): 12–19. [14]Kiani F, Seyyedabbasi A, Aliyev R, et al. Adapted-RRT: novel hybrid method to solve three-dimensional path planning problem using sampling and metaheuristic-based algorithms. Neural Computing and Applications, 2021, 33(24): 17129–17159.