SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking

Autonomous parking fundamentally differs from on-road driving due to its frequent direction changes and complex maneuvering requirements. However, existing End-to-End (E2E) planning methods often simplify the parking task into a geometric path regression problem, neglecting explicit modeling of the vehicle's kinematic state. This"dimensionality deficiency"easily leads to physically infeasible trajectories and deviates from real human driving behavior, particularly at critical gear-shift points in multi-shot parking scenarios. In this paper, we propose SunnyParking, a novel dual-branch E2E architecture that achieves motion state awareness by jointly predicting spatial trajectories and discrete motion state sequences (e.g., forward/reverse). Additionally, we introduce a Fourier feature-based representation of target parking slots to overcome the resolution limitations of traditional bird's-eye view (BEV) approaches, enabling high-precision target interactions. Experimental results demonstrate that our framework generates more robust and human-like trajectories in complex multi-shot parking scenarios, while significantly improving gear-shift point localization accuracy compared to state-of-the-art methods. We open-source a new parking dataset of the CARLA simulator, specifically designed to evaluate full prediction capabilities under complex maneuvers.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-02-25

• Fields of study

  Computer Science, Engineering

• Identifiers
  arXiv 2602.21682
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

  2025cited by this paper
• TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parking

  2025cited by this paper
• ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning

  2024cited by this paper
• E2E Parking: Autonomous Parking by the End-to-end Neural Network on the CARLA Simulator

  2024cited by this paper
• HOPE: A Reinforcement Learning-Based Hybrid Policy Path Planner for Diverse Parking Scenarios

  2024cited by this paper
• Quantitative Analysis of Parking Difficulty via Vehicle Kinematics

  2024cited by this paper
• HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

  2024cited by this paper
• Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

  2023cited by this paper
• SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

  2023cited by this paper
• Planning-oriented Autonomous Driving

  2022cited by this paper
• TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving

  2022cited by this paper
• BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

  2022cited by this paper
• ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer

  2022cited by this paper
• nuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

  2021cited by this paper
• Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset

  2021cited by this paper
• DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets

  2021cited by this paper
• BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

  2021cited by this paper
• VTGNet: A Vision-Based Trajectory Generation Network for Autonomous Vehicles in Urban Environments

  2020cited by this paper
• Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D

  2020cited by this paper
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

  2020cited by this paper
• Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments With Multimodal Sensor Fusion

  2020cited by this paper
• Motion Planning Networks: Bridging the Gap Between Learning-Based and Classical Motion Planners

  2019cited by this paper
• Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles

  2019cited by this paper
• Argoverse: 3D Tracking and Forecasting With Rich Maps

  2019cited by this paper
• On the Spectral Bias of Neural Networks

  2018cited by this paper
• Deep learning for decentralized parking lot occupancy detection

  2017cited by this paper
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• CARLA: An Open Urban Driving Simulator

  2017cited by this paper
• End to End Learning for Self-Driving Cars

  2016cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014cited by this paper
• Path Planning for Autonomous Vehicles in Unknown Semi-structured Environments

  2010cited by this paper

• No citing papers are available for this paper.