GithubHelp home page GithubHelp logo

pi-racing's Introduction

Minimum Curvature Trajectory Planning via Probabilistic Inference for an Autonomous Racing Vehicle

Prerequisites

For running the PI Racing matlab code you need the following libraries installed on your system:

  • CMake
    • Version >= 1.65 (sudo apt install cmake)
  • Boost (for GTSAM)
    • Version >= 3.0 (sudo apt install libboost-all-dev)
  • GTSAM (see installation hint below)
  • PI Racing Factors (from this repo)

The code was written and tested on Ubuntu 18.04.6 LTS and Matlab R2021b.

GTSAM

Clone the GTSAM repo from Github and change to its root directory, then:

git checkout wrap-export
mkdir build
cd build
cmake ..
sudo make install

PI Racing Factors

Clone this project and change to its root directory, then:

cd src/cpp
mkdir build && cd build
cmake ..
sudo make install

Matlab

  • There is an example script given called pi_min_curv.m (minimum curvature path)
  • Start the script by opening the src directory in Matlab and running the pi_min_curv.m script to see the optimization for the Berlin 2018 ePrix circuit
  • Change the track_file variable to "modena_2019.csv" to see the results with comparison for the Modena racetrack
  • The script expects the GTSAM matlab library to be in the directory /usr/local/gtsam_toolbox/

Citation

@article{pi-racing,
  author    = {Salman Bari and
               Ahmad Schoha Haidari and
               Dirk Wollherr},
  title     = {A Fast Approach to Minimum Curvature Raceline Planning via Probabilistic
               Inference},
  journal   = {CoRR},
  volume    = {abs/2203.03224},
  year      = {2022},
  url       = {https://arxiv.org/abs/2203.03224},
  eprinttype = {arXiv},
  eprint    = {2203.03224},
  timestamp = {Thu, 10 Mar 2022 14:39:36 +0100}
}

pi-racing's People

Contributors

ashn-1 avatar

Stargazers

XGW avatar Szymon Kostrubiec avatar

Watchers

 avatar  avatar

pi-racing's Issues

gtsam/matlab issue

Hi, I am trying to use your approach to plan the racing line for an autonomous racing control application. However, I am stuck with some issues.
First, upon building with cmake I encountered an error with matlab_wrap function :
{CMake Error at CMakeLists.txt:95 (matlab_wrap):
matlab_wrap Function invoked with incorrect arguments for function named:
matlab_wrap}
so I changed line 95 of CMakeLists.txt into what was proposed by varunagrawal in borglab/wrap#136 (comment)
I used {matlab_wrap(pi_racing.i ${CONVENIENCE_LIB_NAME} "gtsam;${CONVENIENCE_LIB_NAME}" "" "" "")}. building with the modified CMakeLists.txt worked fine and installation was successful.
but the problem I am facing is when I tried to run pi_min_curv.m example I got the following error in Matlab :
{Unable to resolve the name 'noiseModel.Gaussian.Covariance'.
Error in pi_min_curv (line 121)
bounding_model = noiseModel.Gaussian.Covariance(eye(2) * bounding_sigma);}

and I have no clue whether my installation of pi-racing was faulty or the problem is in linking matlab with gtsam??
Also, the gtsam_toolbox folder contains only pi_racing_wrapper.mexa64 and a folder named +pi-racing with 3 matlab files only is this normal ?

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.