Skip to main content

GPAD for CARLA PythonAPI

Project description

GPAD

GPAD for CARLA PythonAPI

Forward

I finished my Ph.D. and I don't expect to spend much time on this project anymore. But I shared it on GitHub just in case.

The code is not super explicit... So if you have questions or issues, don't hesitate to open an issue on the GitHub page, I would answer you when I can :blush:.

If you want to use this code or the methods detailed in it, please cite me. I first mentioned this code at ICARCV2020 in the following paper Safe Geometric Speed Planning Approach for Autonomous Driving through Occluded Intersections. R. Poncelet, A. Verroust-Blondet and F. Nashashibi. [PDF]

@inproceedings{poncelet:hal-02967740,
 TITLE = {{Safe Geometric Speed Planning Approach for Autonomous Driving through Occluded Intersections}},
 AUTHOR = {Poncelet, Renaud and Verroust-Blondet, Anne and Nashashibi, Fawzi},
 URL = {https://hal.science/hal-02967740},
 BOOKTITLE = {{ICARCV 2020 - 16th International Conference on Control, Automation, Robotics and Vision}},
 ADDRESS = {Shenzhen, China},
 SERIES = {16th International Conference on Control, Automation, Robotics and Vision},
 YEAR = {2020},
 MONTH = Dec
}

Requirements

This package is made to be cloned into the "PythonAPI" folder in CARLA. I also packaged it to allow "import GPAD".

It should run on Carla 0.9.14.

You can check the requirements.txt file.

Structure

Example

  • main.py is an example to run the GPAD Planner detailed (in French) in my Ph.D. thesis.

Packages

  • The Common package contains GPAD Planner, World Manager, and Utils.
  • The Approaches package contains:
  • MMRIS
  • SGSPA
  • Common

Methods

MMRIS

The MMRIS method is detailed (in French) in my Ph.D. thesis. This method is based on this paper (in English) RIS.

  • RIS are calculated for different speed profiles. I compute three speed profiles:
  • A brake speed profile
  • A constant speed profile
  • And an acceleration speed profile
  • Paths are computed for each speed profile
  • The "fastest" speed profile is selected

SGSPA

The SGSPA is detailed in the following paper: Safe Geometric Speed Planning Approach for Autonomous Driving through Occluded Intersections

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gpad-0.0.1.tar.gz (151.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gpad-0.0.1-py3-none-any.whl (261.8 kB view details)

Uploaded Python 3

File details

Details for the file gpad-0.0.1.tar.gz.

File metadata

  • Download URL: gpad-0.0.1.tar.gz
  • Upload date:
  • Size: 151.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for gpad-0.0.1.tar.gz
Algorithm Hash digest
SHA256 562f4443153d427f3909253184548cc246735633b336c964350bfe4eada568c9
MD5 9e4c90f0fa75f509de114451c81073ed
BLAKE2b-256 29bbcaf0e67d6276c2e16749ccbe94f955518a1a7d1df6330277622b285070b1

See more details on using hashes here.

File details

Details for the file gpad-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: gpad-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 261.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for gpad-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c96df6bca2cda29a1d2a167e482a7b7f37c14e53f3fe5fb87d26b17421ee3d12
MD5 6f14aa30d96ec136c9b6bf118f65f0d8
BLAKE2b-256 9cd71c811b11bfdf8657dfb77b6145af2e4614ac2dfc363074b750638311ac31

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page