OPOF simple navigation domains in a 2D grid world to help users familiarize with OPOF. They also act as a sanity check for developing optimization algorithms.
opof-grid2d
is maintained by the Kavraki Lab at Rice University.
$ pip install opof-grid2d
opof-grid2d
is officially tested and supported for Python 3.9, 3.10.
from opof_grid2d.domains import RandomWalk2D
domain = RandomWalk2D(11) # Creates a RandomWalk2D domain instance for a 11x11 board.
An agent starts at a location (green) and moves in random directions according to some fixed probabilities until it reaches the goal (magenta). When attempting to move into an obstacle (black) or the borders of the grid, a step is spent but the position of the agent does not change. The probability of moving in each direction is fixed across all steps.
We want to find a generator that maps a problem instance
The training set and testing set each contain
from opof_grid2d.domains import Maze2D
domain = Maze2D(11) # Creates a Maze2D domain instance for a 11x11 board.
A* search is run against a heuristic function
We want to find a generator
The planning objective
The training set and testing set each contain
If you use opof-grid2d
, please cite us with:
@article{lee23opof,
author = {Lee, Yiyuan and Lee, Katie and Cai, Panpan and Hsu, David and Kavraki, Lydia E.},
title = {The Planner Optimization Problem: Formulations and Frameworks},
booktitle = {arXiv},
year = {2023},
doi = {10.48550/ARXIV.2303.06768},
}
opof-grid2d
is licensed under the BSD-3 license.
opof-grid2d
is maintained by the Kavraki Lab at Rice University, funded in part by NSF RI 2008720 and Rice University funds.