提出SunnyParking，让自动驾驶泊车更像人，精准预测换挡点。
SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking
- 双分支结构同时预测轨迹与换挡状态，实现运动状态感知。
- 在复杂多段泊车中，换挡点定位精度显著优于现有方法。
- 新数据集+傅里叶特征表示，提升目标交互精度与泛化能力。
自动驾驶泊车因频繁变向和复杂操作区别于道路行驶。现有端到端规划方法常将泊车简化为几何路径回归，忽略车辆运动状态的显式建模，导致轨迹物理不可行且偏离真实人类驾驶行为，尤其在多段泊车的关键换挡点。本文提出SunnyParking，一种双分支端到端架构，通过联合预测空间轨迹与离散运动状态序列（如前进/倒车），实现运动状态感知。此外，引入基于傅里叶特征的目标车位表示，克服传统鸟瞰图（BEV）分辨率限制，提升高精度目标交互能力。实验表明，该框架在复杂多段泊车场景中生成更鲁棒、更类人的轨迹，换挡点定位精度显著优于当前最优方法。我们开源了基于CARLA模拟器的新泊车数据集，专用于评估复杂操作下的完整预测能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。