search

onlytailei / carla_cil_pytorch

A pytorch implementation to train the conditional imitation learning policy in "Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective".
BSD 2-Clause "Simplified" License
65 stars 10 forks source link

Test Result #3

Closed kimna4 closed 5 years ago

kimna4 commented 5 years ago

Thank you for sharing this project.

Can you achieve the same result with the paper (CARLA: An Open Urban Driving Simulator) using this project?

I can't take the released results. Thank you

onlytailei commented 5 years ago

I haven't really set up the experiments for the Carla paper. On the other hand, the data augmentation methods are from their ICRA2018 paper. Actually, I used a different dataset separation for my work in End-to-end driving deploying and VR-Goggles. The details can be found in the supplement file.