search

jchengai / planTF

[ICRA'2024] Rethinking Imitation-based Planner for Autonomous Driving
https://jchengai.github.io/planTF/
150 stars 10 forks source link

Ego vs. other agents training #22

Open YasinSonmez opened 6 days ago

YasinSonmez commented 6 days ago

I'm trying to understand the training process. I'm not sure if trajectory generation for the ego vehicle is handled differently from the prediction of other agents. Are there any specific considerations for the ego vehicle compared to the other agents during the training of the transformer model or are we doing the same thing for ego and other agents?

jchengai commented 5 days ago

Hi @YasinSonmez, data augmentations are only applied to the ego vehicle to address closed-loop problems. Prediction serves as an auxiliary task, providing dense supervision, and is not the primary focus of this study.

YasinSonmez commented 5 days ago

I see, can the trajectories of other vehicles be used in the training as if they were ego vehicles to augment the data?

On Thu, Jun 27, 2024 at 8:40 PM Jie Cheng @.***> wrote:

Hi @YasinSonmez https://github.com/YasinSonmez, data augmentations are only applied to the ego vehicle to address closed-loop problems. Prediction serves as an auxiliary task, providing dense supervision, and is not the primary focus of this study.

— Reply to this email directly, view it on GitHub https://github.com/jchengai/planTF/issues/22#issuecomment-2196074399, or unsubscribe https://github.com/notifications/unsubscribe-auth/AI6FYHNEACGM56WZ2AR2KRDZJTLLTAVCNFSM6AAAAABJ637WF2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOJWGA3TIMZZHE . You are receiving this because you were mentioned.Message ID: @.***>