Question about the scenario file in this code

[xinshuoweng]

Make sure you have read FAQ before posting. Thanks!

Hi Dian,

Thank you for your great work! I have one simple question regarding this file: https://github.com/dotchen/WorldOnRails/blob/release/assets/all_towns_traffic_scenarios.json

This file seems to have much more scenarios than the Carla official scenario files, including the old one and also the new one updated 4 months ago: the old one (with 38894 lines): https://github.com/bradyz/leaderboard/blob/7104247204e0e591d43640d2c98490533bc5bbb8/data/all_towns_traffic_scenarios_public.json the new one (with 14986 lines): https://github.com/carla-simulator/leaderboard/blob/master/data/all_towns_traffic_scenarios_public.json

So my question is did you create this file with 102605 lines (https://github.com/dotchen/WorldOnRails/blob/release/assets/all_towns_traffic_scenarios.json) yourself? Or where did you get this scenario file?

Thanks in advance! Xinshuo

[dotchen]

Hi Xinshuo,

Thank you for your interest in our project! The scenario file used in this repo is taken from the leaderboard branch from the scenario_runner, which is the branch that the leaderboard use. https://github.com/carla-simulator/scenario_runner/blob/leaderboard/srunner/data/all_towns_traffic_scenarios.json

[xinshuoweng]

Interesting! I did not notice there are scenario files here as well. Not sure what's the difference from the one in the leaderboard folder though: https://github.com/carla-simulator/leaderboard/blob/master/data/all_towns_traffic_scenarios_public.json

I should probably ask the Carla people about this. But it seems like the one under the leaderboard folder (updated 4 months ago) is newer than the one in the scenario_runner folder (updated 2 years ago), so maybe it is better? Unclear how much performance will be affected using different scenario files to generate data though.

Thanks again!

[dotchen]

Sure thing!

P.S: the one in the master branch might have been updated to accommodate the new CARLA versions (>=0.9.12). So for training models for leaderboard purposes I would recommend sticking to the leaderboard branch. I am not 100% sure about this though.