Giter Site home page Giter Site logo

seawee1 / driver-dojo Goto Github PK

View Code? Open in Web Editor NEW
62.0 2.0 7.0 61.94 MB

A benchmark towards generalizable reinforcement learning for autonomous driving.

License: Other

Python 92.46% Jupyter Notebook 7.47% Shell 0.07%
autonomous-driving carla-simulator generalization gym gym-environment opendrive pcg reinforcement-learning reinforcement-learning-environments rl

driver-dojo's Issues

Scenario composability

Right now, randomized scenarios are mutually exclusive. This means that, e.g., an intersection can not be chained with a subsequent roundabout into one training scenario. Enabling this shouldn't be too hard, but will require some additional work.

Update licenses

Update the repository license and add licence for third-party source code included inside our repository.

driver-dojo + DI-engine

Hi, I am the developer of DI-engine. I am interested to add a demo/example about using the DRL algorithm in DI-engine on driver-dojo. Can you provide some help and advice? Thanks a lot.

Occupancy Grid

Hello,

I hope this finds you well,

Is it possible to implement occupancy grids in driver dojo.

Regards,
Adi

Subclass components into VehicleAttachment and Steppable children

Right now we have multiple components that are either something like

  • an attachment to the ego vehicle or
  • follow the OpenAI gym step, reset, ... interface

Subclassing the second would allow for automated stepping and resetting through some registering mechanism.

Code documentation

Eventhough the current state could be enough, it might make sense to invest a few hours to create some additional documentation lines and clean PEP257 docstrings.

Refactor core scenario source structure

As of right now, the core generalization scenarios are very entangled with the DriverDojoEnv source code. It would be much nicer to have every environment as a single file, including specific ego and traffic initialization as well as traffic spawn methods.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.