Giter Site home page Giter Site logo

planrob-23-low-makespan's Introduction

This repository contains the code that was used for the paper "Towards computing low-makespan solutions for multi-arm multi-task planning problems". A writeup of the content can be found here, and the paper itself is here. It is under active development, the version that was used to produce the result in the paper is tagged.

Installation

The code depends on rai and rai-robotModels. The path to rai needs to be added in the Makefile, and rai-robotModels should be in the same parent forlder as this project.

Compilation then works with

make -j8

In case of issues, try

make cleanAll

To update dependencies

make depend

Also have a look at the intructions in 'rai'.

Usage

Flags:

  • mode [test/show_plan/random_search/greedy_random_search/simulated_annealing]
  • pnp [true/false]
  • stippling_pts [lots]
  • env [lab/'']

To Do

Misc

  • Ensure correct dependencies of rai/rai-robotModels: possibly make a submodule
  • Tests
  • Performance benchmark to ensure changes improve things
  • Optimization benchmark to compare different search approaches

Code

  • split main planning subroutine
  • fix loading and visualization of previously computed paths
  • get rid of warnings

Speed improvements

  • squeaky wheel planner
  • simulated annealing
  • speed up komo runs
  • more sensible search approach: use the fact that we can cache the end

Capabilities

  • enable things that are not only 'go to point', e.g. drawing a line
  • Take multiple poses into account for 'go to point' tasks
  • enable search over sequences with precendence constraints
  • time-rescale path
  • enable multi-arm cooperation
  • look into more complex motion planning:
    • joint optimization
    • constrained sampling based planning
    • inspired by the CMA-ES method?
  • more statistics
  • joint optimization over the whole path
  • reuse more computations (e.g., dummy paths)
  • better (closed form?) approximation of lower bound

Execution

  • Replanning?
  • Controller synthesis
  • Optimizing for robustness

Citation

If you use this codebase in your research, please cite the paper where the codebase is from as

@misc{23-hartmann-ICAPSws-robplan,
  title = {Towards computing low-makespan solutions for multi-arm
  		  multi-task planning problems},
  author = {Hartmann, Valentin N. and Toussaint, Marc},
  year = {2023},
  howpublished = {ICAPS Workshop on Planning and Robotics},
  arxiv_pdf = {2305.17527}
}

planrob-23-low-makespan's People

Watchers

Valentin Hartmann avatar

Forkers

yuezhezhang

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.