GI-SAC: Geometric-Prior-Guided and Intent-Driven Soft Actor-Critic for Autonomous Parking
Applied Sciences · 06.11.2026 · 16 (21) · 11011
DOI: 10.3390/app162111011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.11.2026. Verfasst von Jinhui Gao und 7 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Autonomous parking is an essential component of safe and efficient urban autonomous driving. However, complex constraints in unstructured and confined environments pose significant challenges to parking decision-making. Rule-based planners explicitly account for geometric and kinematic constraints, but their computational demands can increase with the complexity of parking environments. Reinforcement learning offers flexible closed-loop decision-making, yet effective exploration remains challenging in confined spaces. To leverage the strengths of both approaches, this paper proposes Geometric-Prior-Guided and Intent-Driven Soft Actor-Critic (GI-SAC), a closed-loop autonomous parking method integrating geometric-prior guidance with intent-driven representation. First, a coarse Hybrid A* (HA*) trajectory is incorporated into the policy observation and used to construct an auxiliary reward based on the vehicle’s distance to the reference path, with a gradually decaying reward weight regulating the guidance strength. Second, the target parking pose and coarse trajectory are jointly encoded as parking intent, which guides the aggregation of relevant local environmental features through cross-attention. Finally, a spatiotemporal action mask combines spatial feasibility weights with temporal weights based on candidate-action changes relative to the previously executed command, promoting steering continuity through joint weighting and resampling. Evaluations on the Tactics2D simulation platform show that GI-SAC achieves an average success rate of 99.05% across four test scenarios, with success rates of 98.30% and 98.70% in the Difficult and Dragon Lake Parking (DLP) scenarios, respectively, and reduces failures caused by boundary violations and timeouts. Ablation studies and action-variation analyses further demonstrate the contributions of the proposed modules to parking performance and steering-command continuity.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Gao, J., Zhang, Y., Fan, M., Zhai, X., Yuan, H., Jiang, L., Xie, Y., & Yin, Z. (2026). GI-SAC: Geometric-Prior-Guided and Intent-Driven Soft Actor-Critic for Autonomous Parking. Applied Sciences, 16(21), 11011. https://doi.org/10.3390/app162111011
Vancouver
Gao J, Zhang Y, Fan M, Zhai X, Yuan H, Jiang L, et al. GI-SAC: Geometric-Prior-Guided and Intent-Driven Soft Actor-Critic for Autonomous Parking. Applied Sciences. 2026;16(21):11011. doi:10.3390/app162111011
BibTeX
@article{Gao2026,
author = {Gao, Jinhui and Zhang, Yijie and Fan, Mingxin and Zhai, Xukai and Yuan, Hao and Jiang, Longfei and Xie, Ying and Yin, Zhishuai},
title = {GI-SAC: Geometric-Prior-Guided and Intent-Driven Soft Actor-Critic for Autonomous Parking},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {21},
pages = {11011},
doi = {10.3390/app162111011}
}
EUVIMED