MLJejuCamp2017 / DRL_based_SelfDrivingCarControl

Deep Reinforcement Learning (DQN) based Self Driving Car Control with Vehicle Simulator
293 stars 95 forks source link

About the sensors and simulator scripts #16

Open ghost opened 5 years ago

ghost commented 5 years ago

Hi, congratulate won the camp, and the paper was accepted to iv 2018!

In the README.md , you have mentioned " I used lots of vehicle sensors(e.g. RADAR, LIDAR, ...) to perceive environments around host vehicle. Also, There are a lot of Advanced Driver Assistant Systems (ADAS) which are already commercialized."

Thanks.

Kyushik commented 5 years ago

Hello. Thanks for having interest in my project. The LIDAR sensor and Vision are already implemented in the Unity environment. You can get the values through VectorObservation and VisualObservation. Also, I am considering about uploading all of the Unity codes of my environment without purchased model.

ghost commented 5 years ago

Thank you for the reply,

I'm build a simulator for autonomous robot using this project as reference.

And I want to find some sensors to simulator the real sensors which can measure the distance between robot and obstacle.

Can you give me some advise?

Thanks.

Kyushik commented 5 years ago

I can give you advise :) If you want to make that kind of sensor with Unity, I think you'd better to use RayCast in Unity. It returns the distance between the agent and obstacle like LIDAR sensor.

ghost commented 5 years ago

Thank you, it's so kind of you (:

tangrui2018 commented 5 years ago

Hi, amazing project!

I have run the jupyter notebook.

And I am confused about the original Unity Environment.

Could you show us the scripts of the academy, agent, and brains or privately 2018tzoe@gmail.com?

Thanks.