armme41

Results 3 issues of armme41

### System information - **OS Platform and Distribution (e.g., Linux Ubuntu 18.04)**: Ubuntu 20.04 - **Apollo installed from (source or binary)**: source - **Apollo version (3.5, 5.0, 5.5, 6.0)**: 6.0...

Module: Others

https://github.com/ApolloAuto/apollo/blob/0e3f5265ce89dae91789aad6cb6ab590abb97fd9/modules/planning/tasks/deciders/open_space_decider/open_space_roi_decider.cc#L1308 When parking space on the left of ADC, parking boundary is like this: ![Screenshot from 2022-07-27 20-49-25](https://user-images.githubusercontent.com/22172840/181251254-ad2fcd84-8642-499f-9169-ee8ed75f837d.png) Found that ``` // reinsert the initial point to the back to...

Module: Planning

我把lane3d_1000/validation/segment-10203656353524179475_7625_000_7645_000_with_camera_labels中每一帧的车道线转换到全局系叠加起来显示(每一帧只考虑自车系25m以内的点) ![Image](https://github.com/user-attachments/assets/25d11c18-7bcb-4431-a3dd-2fd822c0d614) 最右侧车道线有很多outlier点,不理解的是,真值车道线人工标注,怎么会有车道线之外的outlier点 我们的工作是基于OpenLane数据集做车道线建图,效果评测的时候简单的做法是:将单帧建图结果与单帧真值对比。如果我们想将一个segment的整体建图结果做评测,有没有好的建议