ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control

TL;DR

ParkFormer introduces a transformer-based autonomous parking system that learns from expert demonstrations, effectively integrating goal and pedestrian information to achieve high success rates in complex urban parking scenarios.

Contribution

This work presents a novel end-to-end transformer framework with goal embedding and pedestrian-aware control for autonomous parking, outperforming traditional rule-based methods.

Findings

Achieves a 96.57% success rate in parking tasks

Maintains low positional (0.21m) and orientation (0.41°) errors

Demonstrates effectiveness of pedestrian prediction and goal attention modules

Abstract

Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rule-based parking systems struggle with environmental uncertainties and lack adaptability in crowded or dynamic scenes, human drivers demonstrate the ability to park intuitively without explicit modeling. Inspired by this observation, we propose a Transformer-based end-to-end framework for autonomous parking that learns from expert demonstrations. The network takes as input surround-view camera images, goal-point representations, ego vehicle motion, and pedestrian trajectories. It outputs discrete control sequences including throttle, braking, steering, and gear selection. A novel cross-attention module integrates BEV features with target points, and a GRU-based pedestrian predictor enhances safety by modeling dynamic obstacles. We validate our method on the CARLA 0.9.14 simulator in both vertical and parallel parking scenarios. Experiments show our model achieves a high success rate of 96.57\%, with average positional and orientation errors of 0.21 meters and 0.41 degrees, respectively. The ablation studies further demonstrate the effectiveness of key modules such as pedestrian prediction and goal-point attention fusion. The code and dataset will be released at: https://github.com/little-snail-f/ParkFormer.