New model-based manipulation technique for reshaping deformable linear objects

Khalifa, Alaa; Palli, Gianluca

doi:10.1007/s00170-021-08107-x

Cited by 3 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A typical approach to manipulating DLOs is to use their models to plan the motion and control commands necessary to rearrange it to the desired state. In recent years, there were many attempts to develop DLO models, such as FEM-based ones [10], [11], [12], [13], using Cosserat rod theory [14], [15], [16], Kirchoff elastic rod [17], [18] or dynamic B-splines [19], [20]. However, these models make strong assumptions about the properties of the objects or require significant amounts of computations to evaluate, which limits their applicability in real-time manipulation or makes their relevance to the real DLOs questionable.…”

Section: Introductionmentioning

confidence: 99%

Robotic Manipulation of Elongated and Elastic Objects

Kicki

Bednarek

Walas

2019

2019 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)

View full text Add to dashboard Cite

The robotic manipulation of Deformable Linear Objects (DLOs) is a vital and challenging task that is important in many practical applications. Classical model-based approaches to this problem require an accurate model to capture how robot motions affect the deformation of the DLO. Nowadays, data-driven models offer the best tradeoff between quality and computation time. This paper analyzes several learning-based 3D models of the DLO and proposes a new one based on the Transformer architecture that achieves superior accuracy, even on the DLOs of different lengths, thanks to the proposed scaling method. Moreover, we introduce a data augmentation technique, which improves the prediction performance of almost all considered DLO data-driven models. Thanks to this technique, even a simple Multilayer Perceptron (MLP) achieves close to state-of-the-art performance while being significantly faster to evaluate. In the experiments, we compare the performance of the learning-based 3D models of the DLO on several challenging datasets quantitatively and demonstrate their applicability in the task of shaping a DLO.

show abstract