search

TempleRAIL / drl_vo_nav

[T-RO 2023] DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles
https://doi.org/10.1109/TRO.2023.3257549
GNU General Public License v3.0
125 stars 9 forks source link

How to test #29

Open Shiqi-7-7 opened 1 month ago

Shiqi-7-7 commented 1 month ago

Hello, thank you very much for your work. I have read your article and tried to reproduce code.How to test this model? 2024-08-12 18-44-44 的屏幕截图 How do I obtain the curve graph during the training process and the charts(success rate,time,length,speed) in your paper? Thank you very much!

zzuxzt commented 3 weeks ago

Thanks for your interest in our work. If you want to test the trained model, you can deploy the control policy on the robot, publish a predefined series of goal points, and let the robot navigate through a predefined series of goal points around the corresponding test environment. For example, you can publish a set of goal points to test the policy using the following command:

roslaunch drl_vo_nav publish_goal_sequence.launch

You can view the training curve using tensorboard using the following command:

tensorboard --logdir="./runs/"