ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation
For autonomous driving researchers, this work addresses the sample inefficiency and exploration challenges in RL-based parking by incorporating human corrective feedback, though the improvement is incremental over existing RL methods.
This paper introduces a correction-in-the-loop sample-efficient reinforcement learning (CIL-SERL) framework for end-to-end autonomous parking, trained in a photorealistic 3D Gaussian Splatting (3DGS) simulator. The method achieves substantial improvements in parking success rate, operational efficiency, and safety across diverse scenarios, validated in both simulation and on a physical vehicle.
Autonomous parking demands precise low-speed maneuvering within narrow, cluttered, and highly constrained environments, where vehicles must navigate tight spaces while avoiding static obstacles and complex geometric boundaries. Unlike imitation learning, which typically requires massive volumes of high-quality expert demonstrations to converge to a stable policy and often suffers from limited generalization to unseen scenarios, traditional reinforcement learning (RL) methods face persistent challenges including excessive training overhead, inefficient exploration, and even failure to learn viable parking strategies in challenging settings. To address these limitations, this paper presents a correction-in-the-loop sample-efficient reinforcement learning (CIL-SERL) framework for end-to-end autonomous parking, which is entirely trained in a photorealistic 3D Gaussian Splatting (3DGS) parking simulator that enables high-fidelity digital reconstruction of real-world scenes. Inspired by error-correction notebooks used in learning practice, we design a novel multi-level replay buffer mechanism. These buffers hierarchically organize and store standard RL rollouts, human corrective interventions, failed exploration trajectories, and rollback-based correction segments in separate yet interconnected memory regions, facilitating structured sampling and targeted learning during training. The proposed framework is systematically evaluated in both the 3DGS simulation environment and a physical vehicle platform. Extensive experimental results demonstrate that our method achieves substantial improvements in parking success rate, operational efficiency, and safety performance across diverse scenarios, validating the effectiveness and practical applicability of the proposed CIL-SERL-based end-to-end autonomous parking solution.