rizavelioglu/challenge-aido_rl-il

Reinforcement Learning + Imitation Learning based approach to AI Driving Olympics

Hey, this is Riza!

I am a 3rd year Ph.D. student at the University Bielefeld and am currently working on the project Machine Learning for Process Mining (ML4ProM) under the supervision of Prof.Dr.Barbara Hammer and Prof.Dr.Wil van der Aalst. The project is funded by the Ministry of Culture and Science of North Rhine-Westphalia, Germany. Please visit my website for more info: https://rizavelioglu.github.io/

Recent Works:

• Detecting Hate Speech In Multimodal Memes Using Vision-Language Models
  _{R Velioglu
  M.Sc. Thesis (2021)}


• Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge
  _{R Velioglu, J Rose
  Presented at NeurIPS (2020)}

Languages and Tools:

Connect with Me:

Profile Views:

challenge-aido_rl-il's Issues

Confusion about the simulation environment

Hello,

I have a little confusion about the gym-duckietown simulator. My confusion is how does the robot moves forward and avoids obstacles?

For example, in the PID controller script, I didn't see the implementation of controlling the robot to move forward and avoid obstacles. But it can do this in the simulation after I run this script. According to my understanding, it is mainly for path tracking. Does the simulator has already provided the motion planning part?

How to add new maps for RL agent to learn?

Currently, there are only three maps in which RL agent will learn driving. If I want to add more scenarios ( e.g. a straight road with a static obstacle in the middle of the road), how could I do that?

I found that when I run 'get_tile_coordinates.py' script, if I set the map_names as my new map, it will has this error:

Traceback (most recent call last):
File "get_tile_coordinates.py", line 79, in
tile_coord = env._get_tile(i, j)['coords']
TypeError: 'NoneType' object is not subscriptable

ModuleNotFoundError: No module named 'duckietown_world'

When i run:
python log.py
I got this error:
Traceback (most recent call last):
File "log.py", line 7, in
from duckietown_rl.gym_duckietown.simulator import Simulator
File "../duckietown_rl/gym_duckietown/simulator.py", line 10, in
from duckietown_world.world_duckietown.pwm_dynamics import get_DB18_nominal, get_DB18_uncalibrated
ModuleNotFoundError: No module named 'duckietown_world'

Error operatorPrecedence' from 'pyparsing' - Google Colab

Hello @rizavelioglu,

first of all I want to thank you for your repository for those of us who are starting to learn IA in robotics.

I am trying to run google colab but unfortunately there is an error in the pyparsing library, I tried to install the version you used in the execution of your google colab but I could not solve the error.

I hope you can help me because your repository is very good to learn.

thank you very much

Raúl