ManipulationPlanning-SI-RRT

Combination of Rapidly-Exporing Random Trees (RRT) and Safe Interval Path Planning (SIPP) for high-DOF planning in dynamic environments, i.e. planning a path for a manipulator when moving obstacles are present (and their trajectories are know/accurately predicted)

Important

This repository contains code for the paper:

Kerimov N., Onegin A, Yakovlev K. Safe Interval Randomized Path Planning For Manipulators.

[Full text on arXiv]

Overview

This repository contains the source code for path planning in dynamic enviroments for manipulators and Blender plugins and code for creating and visualisation test cases.

Supported Algorithms

The following path planning algorithms are used:

• DRGBT: reactive planner for manipulators. We forked authorss implementation from RPMPLv2 library and modified it to use our collisiion detection functions.
• ST-RRT*: deliberative planner for planning in space-time. We forked authors'implementation from OMPL library.
• SI-RRT: deliberative planner that uses safe intervals for planning in dynamic enviroment.

This repository can also be used as a base framework for implementing custom AMAPF algorithms.

Quick start

Download dataset https://disk.yandex.ru/d/-73LOGO5kOSYuA and extract ./tests directory in ./mass_test/tests

Set number of parallel jobs in ./mass_test/do_mass_test.py NUM_CPUS. best practice - set NUM_CPUS as number of cores in CPU - 1

Download docker container, remove tests results from the dataset, enter the container

make pull_docker
make clean_experiments_result
make enter_debug_docker

cd ./app

build planners and start mass test execution

make build_planner_debug
make mass_tests

Analyse data

Use ./mass_test/final_analysis.ipynb to analyse planner execution data

Data, that has been used in the paper is available at https://disk.yandex.ru/d/-73LOGO5kOSYuA

Citing This Work

If you use this repository in your research, please cite the following paper:

@misc{kerimov2025safeintervalrandomizedpath,
      title={Safe Interval Randomized Path Planning For Manipulators}, 
      author={Nuraddin Kerimov and Aleksandr Onegin and Konstantin Yakovlev},
      year={2025},
      eprint={2412.19567},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2412.19567}, 
}

Contact

For questions or further information, please contact:

• Kerimov Nuraddin (kerimov.nm@phystech.edu)