https://github.com/psodhi/tactile-in-hand

https://github.com/psodhi/tactile-in-hand

Last synced: 5 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/psodhi/tactile-in-hand
• Owner: psodhi
• License: bsd-3-clause
• Created: 2021-11-15T01:09:08.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2022-06-20T06:33:28.000Z (over 2 years ago)
• Last Synced: 2024-08-02T08:06:38.415Z (4 months ago)
• Language: Python
• Size: 116 KB
• Stars: 13
• Watchers: 1
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-tactile-sensing - PatchGraph:In-hand tactile tracking with learned surface normals

README

        
PatchGraph

===================================================

This repository contains the source code of the paper [PatchGraph: In-hand tactile tracking with learned surface normals](https://arxiv.org/abs/2111.07524).

# Installation

Create a virtual python environment using [Anaconda](https://www.anaconda.com/products/individual):

```

conda create -n inhand python=3.7

conda activate inhand

```

Install the `inhandpy` python package. From the base directory execute:

```

cd inhandpy/

pip install -e .

```

# Usage

In `inhandpy`, download datasets, pre-trained models and other local resources by running:

```

./download_local_files.sh

```

## Stage 1: Tactile images to 3D point clouds

To run the example:

```

python scripts/examples/digit_rgb_to_cloud3d.py

```

By default, this runs the sim trials with cube shape. To run the example with other datasets and settings, please look at user set options under [digit_rgb_to_cloud3d.yaml](inhandpy/config/digit_rgb_to_cloud.yaml).