Constarium
← Search

Data · dataset · 2026

Replication Data for: Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short Term Memory Learning

Listed in DaRUS

This dataset contains all trainingsdata and model weights which are used within the paper "Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short Term Memory Learning".

Description

The manipulation of Deformable Linear Objects (DLOs) such as cables poses a significant challenge for automation due to their infinite degrees of freedom and non-linear dynamics. In this paper we present a machine learning based optimal control approach for the manipulation of DLOs.

This approach is divided into two main components: modeling and control. For modeling the dynamics of the DLO, we propose a learning based approach using a bidirectional Long Short-Term Memory (biLSTM) network. The biLSTM network is trained on synthetic data generated by the MuJoCo physics engine.

Read the rest (2 more)

For manipulating the DLO, a model predictive control strategy that employs Model Predictive Path Integral (MPPI) control is selected. The proposed approach is evaluated through simulation and experiments. The results demonstrate the effectiveness of the proposed method in achieving accurate and efficient manipulation of DLOs.

The dataset contains the following files: model weights biLSTM_bs128_hs256_lr00001_epochs50_10k.pth biLSTM_bs128_hs256_lr00001_epochs50_20k.pth biLSTM_bs128_hs256_lr00001_epochs50_30k.pth rollout dataset (rollout.npz) trainingdata dataset_10k.npz dataset_20k.npz dataset_30k.npz python file for extracting data from .npz files (getDataset.py)

Links

Where it is published

Catalogue records · 1

Topics

Stated by source
Engineering
From keywords
Engineering
Provenance · 1 source records, 10 field assertions
SourceKeyLast seenRaw
DaRUSdoi:10.18419/DARUS-505011 d agoJSON v1
FieldAssertionExtractorEvidence
concepts[field].anzsrc:group:4007enrichment · darus uni stuttgart detaxonomy-embedding@1.1.0title+keywords+description (70%)
concepts[field].dataverse_subject:engineeringsource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0/subjects
concepts[field].local:field:engineeringmapping · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0/subjects
concepts[method].local:method:simulationenrichment · darus uni stuttgart dekeyword-concept-rules@1.0.0title+description (75%)
created_datesource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0
descriptionsource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0/description
publication_datesource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0
titlesource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0/name
updated_datesource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0
version_labelsource · darus uni stuttgart deconnector:darus_uni_stuttgart_de@1.0.0