E2E Parking Dataset: An Open Benchmark for End-to-End Autonomous Parking

--While traditional autonomous driving methods with multi-stage pipelines suffer from lengthy processes, error accumulations and maintenance difficulties, the end-to-end method is designed to map the data of multiple sensors directly into motion control commands, with high flexibility, efficiency and generalization. Therefore, the end-to-end model has shown great potential in autonomous driving. Due to the low speed, low risk, and low complexity characteristics of autonomous parking scenarios, end-to-end methods can be applied to autonomous parking systems earlier . While prior work introduced a visual-based parking model and a pipeline for data generation, training and closed-loop test, the dataset itself was not released. T o bridge this gap, we work on creating large end-to-end autonomous parking datasets in CARLA based on the prior work'E2E Parking'. Keyboard control is replaced by Handle Controller to improve usability, efficiency, and operational precision. During the iterative process of dataset generation, we evaluate the effect of different factors on the parking performance of the controlled vehicle, including diverse scenes generated by multiple random seeds, the position of the roadside object's shadow dependent on weather setting, dataset size, initial learning rate and training epochs. We recommend generating at least 2 scenes for each parking slot with different random seeds, where 8 trajectories with different initial positions are collected for each scene. Weather settings should be modified to make the dataset include scenes with shadow projected on the target slot. Experiments demonstrate that an initial learning rate of 7. 5 10 After several iterations, we are able to open-source a high-quality dataset for end-to-end autonomous parking.