ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning

TL;DR

This paper introduces ParkingE2E, an end-to-end neural network that uses imitation learning and transformer-based decoding to improve autonomous parking from images to planning, achieving high success rates in real-world tests.

Contribution

It presents a novel end-to-end parking framework employing a transformer decoder and imitation learning, advancing beyond traditional rule-based methods.

Findings

Achieved an average parking success rate of 87.8% in real-world scenarios.

Validated the approach with real-vehicle experiments.

Demonstrated effectiveness across four different parking garages.

Abstract

Autonomous parking is a crucial task in the intelligent driving field. Traditional parking algorithms are usually implemented using rule-based schemes. However, these methods are less effective in complex parking scenarios due to the intricate design of the algorithms. In contrast, neural-network-based methods tend to be more intuitive and versatile than the rule-based methods. By collecting a large number of expert parking trajectory data and emulating human strategy via learning-based methods, the parking task can be effectively addressed. In this paper, we employ imitation learning to perform end-to-end planning from RGB images to path planning by imitating human driving trajectories. The proposed end-to-end approach utilizes a target query encoder to fuse images and target features, and a transformer-based decoder to autoregressively predict future waypoints. We conducted extensive experiments in real-world scenarios, and the results demonstrate that the proposed method achieved an average parking success rate of 87.8% across four different real-world garages. Real-vehicle experiments further validate the feasibility and effectiveness of the method proposed in this paper.