MCZhi / DIPP

[TNNLS] Differentiable Integrated Prediction and Planning Framework for Urban Autonomous Driving
https://mczhi.github.io/DIPP/
197 stars 40 forks source link

Consult the data preprocessing problems #13

Closed TimHo0331 closed 1 year ago

TimHo0331 commented 1 year ago

Dear authors, Very thankful for providing the code! A very interesting work! May I ask a question about data preprocessing of the map? Does the map_api in data_utils.py and data_proprocess.py refer to some other materials? (e.g. find the route, depth first search, generate target course,...) This part is kind of difficult to understand. And I want to ask if you could refer to some materials to help me know how to preprocess the lane graph? Thank you so much!

MCZhi commented 1 year ago

Hi, @panda2020-sky, thank you for your interest. Part of the code is borrowed from argoverse map_api (e.g., dfs) and python robotics (e.g., generate target course). You may check their code to know the details.