Automated Valet Parking (AVP) is a crucial component of advanced autonomous
driving systems, focusing on the endpoint task within the "human-vehicle
interaction" process to tackle the challenges of the "last mile".The perception
module of the automated parking algorithm has evolved from local perception
using ultrasonic radar and global scenario precise map matching for
localization to a high-level map-free Birds Eye View (BEV) perception
solution.The BEV scene places higher demands on the real-time performance and
safety of automated parking planning tasks. This paper proposes an improved
automated parking algorithm based on the A* algorithm, integrating vehicle
kinematic models, heuristic function optimization, bidirectional search, and
Bezier curve optimization to enhance the computational speed and real-time
capabilities of the planning algorithm.Numerical optimization methods are
employed to generate the final parking trajectory, ensuring the safety of the
parking path. The proposed approach is experimentally validated in the commonly
used industrial CARLA-ROS joint simulation environment. Compared to traditional
algorithms, this approach demonstrates reduced computation time with more
challenging collision-risk test cases and improved performance in comfort
metrics.

基于 A * 算法，结合车辆运动学模型、启发式函数优化、双向搜索和贝塞尔曲线优化的改进型自动停车算法，提高了算法的计算速度和实时能力，并利用数值优化方法生成最终停车轨迹，确保了停车路径的安全性。与传统算法相比，该方法在更具挑战性的碰撞风险测试案例中计算时间减少，并在舒适性指标上的性能提升。

基于视觉的 BEV 自动停车规划

Automated Parking Planning with Vision-Based BEV Approach

Environmental perception in Automated Valet Parking (AVP) has been a
challenging task due to severe occlusions in parking garages. Although
Collaborative Perception (CP) can be applied to broaden the field of view of
connected vehicles, the limited bandwidth of vehicular communications restricts
its application. In this work, we propose a BEV feature-based CP network
architecture for infrastructure-assisted AVP systems. The model takes the
roadside camera and LiDAR as optional inputs and adaptively fuses them with
onboard sensors in a unified BEV representation. Autoencoder and downsampling
are applied for channel-wise and spatial-wise dimension reduction, while
sparsification and quantization further compress the feature map with little
loss in data precision. Combining these techniques, the size of a BEV feature
map is effectively compressed to fit in the feasible data rate of the NR-V2X
network. With the synthetic AVP dataset, we observe that CP can effectively
increase perception performance, especially for pedestrians. Moreover, the
advantage of infrastructure-assisted CP is demonstrated in two typical
safety-critical scenarios in the AVP setting, increasing the maximum safe
cruising speed by up to 3m/s in both scenarios.

自动泊车系统中加强环境感知一直是一个困难的任务，但是通过协同感知可以扩大车辆的视野，本文提出了一种基于 BEV 特征的协同感知网络架构，通过将道路边缘摄像机和激光雷达与车载传感器融合，有效地压缩 BEV 特征图的大小以适应 NR-V2X 网络的数据速率。通过合成的 AVP 数据集，我们观察到协同感知可以有效地提高感知性能，特别是对于行人。此外，在两种典型的安全关键场景中展示了基础设施辅助式协同感知的优势，在这两种场景中，最大安全巡航速度提高了 3m/s。