Skip to main navigation Skip to search Skip to main content

Tackling Narrow-Space Parallel Parking: Reeds-Shepp-integrated Reinforcement Learning with Learnable Cost Heuristic

  • Shuaicong Yang
  • , Mengying Ruan
  • , Qi Huang
  • , Yi Yang
  • , Ting Zhang*
  • , Mengyin Fu
  • *Corresponding author for this work
  • Beijing Institute of Technology
  • Nanjing University of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Narrow-space parallel parking is one of the most challenging tasks in autonomous driving, attributed to limited maneuvering space and strict kinematic constraints. Conventional rule-based planners (e.g., Reeds-Shepp (RS) curves) can generate feasible trajectories but suffer from high computational costs and limited adaptability in narrow environments. Recent reinforcement learning (RL) approaches offer enhanced flexibility, yet their performance degrades under severe spatial constraints and nonholonomic vehicle dynamics. To address these issues, this work proposes a learnable RS-integrated reinforcement learning framework. First, a learnable RS cost field based on attention networks is developed to encode kinematic feasibility and provide soft heuristic guidance for reward design. Then, by fusing the RS-guided reward with a direct parking reward under a dual-critic architecture, the framework effectively integrates rule-based priors with the adaptability of RL. Experimental results show that the proposed learnable RS field accurately generates RS cost distributions with a 161× computational speedup. Compared with baselines, the RS-RL framework improves the success rate by 8.7% and reduces the travel distance by 20.3%. Particularly for narrow parallel parking spaces with a length of only 1.3 times the vehicle length (6.5m), our method attains a 97.8% parking success rate with adequate safety margins, demonstrating superior safety performance and adaptability to narrow parking scenarios.

Original languageEnglish
Title of host publication2026 IEEE Intelligent Vehicles Symposium, IV 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages545-552
Number of pages8
ISBN (Electronic)9798331547936
DOIs
Publication statusPublished - 2026
Event2026 IEEE Intelligent Vehicles Symposium, IV 2026 - Plymouth, United States
Duration: 22 Jun 2026 → 25 Jun 2026

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings
ISSN (Print)1931-0587
ISSN (Electronic)2642-7214

Conference

Conference2026 IEEE Intelligent Vehicles Symposium, IV 2026
Country/TerritoryUnited States
CityPlymouth
Period22/06/26 → 25/06/26

Keywords

  • Learnable Cost Field
  • Narrow-space Parallel Parking
  • Reeds-Shepp Curves
  • Reinforcement Learning

Fingerprint

Dive into the research topics of 'Tackling Narrow-Space Parallel Parking: Reeds-Shepp-integrated Reinforcement Learning with Learnable Cost Heuristic'. Together they form a unique fingerprint.

Cite this