https://github.com/ctu-vras/actsel

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
✓
DOI references
Found 2 DOI reference(s) in README
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (11.0%) to scientific vocabulary

Last synced: 10 months ago · JSON representation

Repository

Basic Info

Host: GitHub
Owner: ctu-vras
License: gpl-3.0
Language: Python
Default Branch: master
Size: 1.83 MB

Statistics

Stars: 1
Watchers: 2
Forks: 0
Open Issues: 0
Releases: 0

Created over 2 years ago · Last pushed over 1 year ago

Metadata Files

Readme License

README.md

Action Selection algorithm to explore the physical properties in broader term.

ACTSEL source code repository

We introduce ACTSEL. A method for automatic selection of actions that help optimally determine physical object properties that are not readily available through vision.

Graphical model overview

General diagram of ACTSEL algorithm in action. Bayesian network

General overview of the algorithm (left), Bayesian network and action relations (right)

Running the model

For best experience install conda environment as numpy, scipy and scikit-learn are needed for algorithm operation 1) To run the model, fill in the templates for nodes, actions and their relevant confusion matrices in configs/templates. In order to update the actual config .json files, run the scripts/templates_to_cfgs.py from root directory as: python3 scripts/templates_to_cfgs.py

2) Customize the main.py to meet your action and object requirements byt customizing experiment_object_names and action to node mapping.

Implementation remarks

The algorithm and results presented in the paper were obtained offline on pre-measured dataset for broader statistical understanding. This fact is reflected in main.py.

Publication, video, data

Kruzliak, A.; Hartvich, J.; Patni, S. P.; Rustler, L.; Behrens, J. K.; Abu-Dakka, F. J.; Mikolajczyk, K.; Kyrki, V. & Hoffmann, M. (2024). Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements, in 'Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on', pp. 7596-7603. * Full text: DOI - IEEE Xplore , pdf-arxiv * Video: youtube * Database of object measurements and its source code: link

Owner

Name: Vision for Robotics and Autonomous Systems
Login: ctu-vras
Kind: organization
Location: Prague

Website: https://cyber.felk.cvut.cz/vras
Repositories: 24
Profile: https://github.com/ctu-vras

Research group at Czech Technical University in Prague (CTU), Faculty of Electrical Engineering, Department of Cybernetics

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science