https://github.com/giuliano-97/active_panoptic_mapping
Informative Planning for Accurate Panoptic Mapping
https://github.com/giuliano-97/active_panoptic_mapping
computer-vision mapping path-planning robotics ros
Last synced: 3 months ago
JSON representation
Informative Planning for Accurate Panoptic Mapping
- Host: GitHub
- URL: https://github.com/giuliano-97/active_panoptic_mapping
- Owner: giuliano-97
- Created: 2022-04-19T14:10:05.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2022-10-07T18:37:21.000Z (almost 4 years ago)
- Last Synced: 2025-10-08T23:25:03.558Z (9 months ago)
- Topics: computer-vision, mapping, path-planning, robotics, ros
- Language: Python
- Homepage:
- Size: 356 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Active panoptic mapping
## Setup
### Dependencies
This project uses [Robostack](https://robostack.github.io/) so only a minimal `conda` installation such as [`mambaforge`](https://github.com/conda-forge/miniforge) is required to get started.
### Installation
1. Create a directory tree for catkin workspace:
```
mkdir -p catkin_ws/src
cd catkin_ws/src
```
1. Clone this repository in the src directory:
```
git clone git@github.com:giuliano-97/active_panoptic_mapping.git
```
1. Make sure `mamba` is install in your `base` environment (not needed when using `mambaforge`), then create the conda environment by running:
```
mamba env create -f environment.yml
```
1. Activate the create conda environment:
```
conda activate active_panoptic_mapping_env
```
1. Initialize the catkin workspace:
```
cd .. && catkin init
catkin config --cmake-args -DCMAKE_BUILD_TYPE=RelWithDebInfo
catkin config --merge-devel
cd src
```
1. Install package dependencies using ros install:
- If you created a new workspace:
```
wstool init . /active_panoptic_mapping/active_panoptic_mapping_ssh.rosinstall
wstool update
```
- If you use an existing workspace. Notice that some dependencies require specific branches that will be checked out.
```
wstool merge -t . ./active_panoptic_mapping/active_panoptic_mapping.rosinstall
wstool update
```
1. Apply some minor patches to the `eigen_catkin` and `opencv3_catkin` packages to avoid compilation errors:
```
bash active_panoptic_mapping/apply_patches.sh
```
1. Compile and source the ros environment:
```
catkin build active_panoptic_mapping_utils
source ../devel/setup.bash
```
## Examples
### Replica Demo
1. Download the Replica dataset by following the download instructions [on the GitHub page](https://github.com/facebookresearch/Replica-Dataset#download-on-mac-os-and-linux).
1. Launch the `active_panoptic_mapping_node` on the Replica "FRL-Apartment-0" scene:
```
roslaunch active_panoptic_mapping_ros run.launch datasets_dir:=$(dirname )
```
1. Start publishing simulated sensor data:
```
rosservice call /habitat_sim_node/toggle_pub_sensor_data true
```
1. Start the planner:
```
rosservice call /active_panoptic_mapping_node/toggle_running true
```
1. By default, this will use the ground truth panoptic labels provided by the simulation. To use panoptic labels predicted online by Mask2Former, you need to additionally pass the use_ground_truth:=false argument:
```
roslaunch active_panoptic_mapping_ros run.launch datasets_dir:=$(dirname ) use_ground_truth:=false
```