TY - GEN
T1 - Tackling Narrow-Space Parallel Parking
T2 - 2026 IEEE Intelligent Vehicles Symposium, IV 2026
AU - Yang, Shuaicong
AU - Ruan, Mengying
AU - Huang, Qi
AU - Yang, Yi
AU - Zhang, Ting
AU - Fu, Mengyin
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - Learnable Cost Field
KW - Narrow-space Parallel Parking
KW - Reeds-Shepp Curves
KW - Reinforcement Learning
UR - https://www.scopus.com/pages/publications/105046883991
U2 - 10.1109/IV66570.2026.11623920
DO - 10.1109/IV66570.2026.11623920
M3 - Conference contribution
AN - SCOPUS:105046883991
T3 - IEEE Intelligent Vehicles Symposium, Proceedings
SP - 545
EP - 552
BT - 2026 IEEE Intelligent Vehicles Symposium, IV 2026
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 June 2026 through 25 June 2026
ER -