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
113 stars 7 forks source link

VO position in the code #13

Closed Alchemistqqqq closed 7 months ago

Alchemistqqqq commented 7 months ago

Hello, before the actual physics experiment, I hope to read the code to deepen my understanding of this work. You used VO in your paper and designed a new reward function based on it. Perhaps due to carelessness, I can't locate it accurately in the code. I hope you can provide some help, thank you very much.

zzuxzt commented 7 months ago

Thank you for your interest in our work. The detailed implementation is in theta_reward.