Learning Visual Feedback Control for Dynamic Cloth Folding

Hietala, Julius; Blanco-Mulero, David; Alcan, Gökhan; Kyrki, Ville

doi:10.1109/iros47612.2022.9981376

Cited by 24 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While we demonstrated the benefit of choosing the primitive parameter values for manipulating multiple cloths, generalising to a broader set of materials and shapes remains an open problem. Recent research by Hietala et al [16] indicates that closed-loop feedback significantly improves the adaptation capabilities in cloth manipulation. Thus, combining parameterised primitives with real-time closed-loop feedback appears as a promising avenue towards more general and adaptive skills.…”

Section: Discussionmentioning

confidence: 99%

“…However, all these works suffer from the same caveat, they focus on determining only the pick and place of pre-defined manipulation primitives, neglecting other parameters such as the velocity at which they are executed. The velocity at which the manipulation actions are executed has an impact in tasks such as cloth folding [16], where dynamic manipulation actions can be adapted according to the fabric material. In this work, we decide parameters such as the velocity for a dynamic manipulation primitive, and the height for a pick-and-place primitive, thus generating a more diverse set of manipulation actions to cope with cloths of varied sizes and materials.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, the network parameters are initialised randomly and no prior is required. Finally, in order to reduce the number of network parameters and based on the results from prior work on cloth manipulation [16], we use a grayscale image s ∈ R 128×128 as input to the network. The observations are rotated at each time-step to help generalise the network to different cloth states.…”

Section: Training Proceduresmentioning

confidence: 99%

See 2 more Smart Citations

QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation

Blanco-Mulero¹,

Alcan²,

Abu‐Dakka³

et al. 2023

Preprint

View full text Add to dashboard Cite

Pre-defined manipulation primitives are widely used for cloth manipulation. However, cloth properties such as its stiffness or density can highly impact the performance of these primitives. Although existing solutions have tackled the parameterisation of pick and place locations, the effect of factors such as the velocity or trajectory of quasi-static and dynamic manipulation primitives has been neglected. Choosing appropriate values for these parameters is crucial to cope with the range of materials present in house-hold cloth objects. To address this challenge, we introduce the Quasi-Dynamic Parameterisable (QDP) method, which optimises parameters such as the motion velocity in addition to the pick and place positions of quasi-static and dynamic manipulation primitives. In this work, we leverage the framework of Sequential Reinforcement Learning to decouple sequentially the parameters that compose the primitives. To evaluate the effectiveness of the method we focus on the task of cloth unfolding with a robotic arm in simulation and real-world experiments. Our results in simulation show that by deciding the optimal parameters for the primitives the performance can improve by 20% compared to sub-optimal ones. Real-world results demonstrate the advantage of modifying the velocity and height of manipulation primitives for cloths with different mass, stiffness, shape and size. Supplementary material, videos, and code, can be found at https://sites.google.com/view/qdp-srl.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Training Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation

Blanco-Mulero¹,

Alcan²,

Abu‐Dakka³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Reinforcement Learning and Learning from Demonstration have demonstrated success in cloth manipulation tasks [13][14][15][16][17]. However, they often require substantial data and are frequently trained in simulation.…”

Section: Introductionmentioning

confidence: 99%

ShakingBot: dynamic manipulation for bagging

Gu,

Zhang,

et al. 2024

Robotica

View full text Add to dashboard Cite

Bag manipulation through robots is complex and challenging due to the deformability of the bag. Based on the dynamic manipulation strategy, we propose a new framework, ShakingBot, for the bagging tasks. ShakingBot utilizes a perception module to identify the key region of the plastic bag from arbitrary initial configurations. According to the segmentation, ShakingBot iteratively executes a novel set of actions, including Bag Adjustment, Dual-arm Shaking, and One-arm Holding, to open the bag. The dynamic action, Dual-arm Shaking, can effectively open the bag without the need to take into account the crumpled configuration. Then, the robot inserts the items and lifts the bag for transport. We perform our method on a dual-arm robot and achieve a success rate of 21/33 for inserting at least one item across various initial bag configurations. In this work, we demonstrate the performance of dynamic shaking action compared to the quasi-static manipulation in the bagging task. We also show that our method generalizes to variations despite the bag’s size, pattern, and color. Supplementary material is available at https://github.com/zhangxiaozhier/ShakingBot.

show abstract

“…On the other hand, dual-arm robots have the advantage of higher manipulation capability and efficiency, although it is also more complicated and the collaboration of two arms must be taken into consideration as well. Consequently, single-arm robots tend to be used mainly for the validation and verification of algorithms of perception and grasping [1][2][3][4], while dual-arm robots [5][6][7][8][9][10][11] concentrate more on the actual application tasks with higher requirement for hardware and technical difficulty, especially on human-like tasks that can only be done with both two arms.…”

Section: Introductionmentioning

confidence: 99%

Development of the “Quad-SCARA” platform and its collision avoidance based on Buffered Voronoi Cell

Sun,

Ishida,

Makino

et al. 2023

Robotica

View full text Add to dashboard Cite

As a solution to soft material manipulation, dual-arm robots that are capable of multi-point grasping have become the latest trend due to their higher capability and efficiency. To explore further development in soft material manipulation and go beyond the hardware limit of dual arms, in this paper the robot platform “Quad-SCARA” that consists of four Selective Compliance Assembly Robot Arm (SCARA) is developed and introduced. With the base of hardware platform, a novel collision avoidance system designed for the motion planning of Quad-SCARA in multi-point grasping state is proposed. This system is inspired by the idea of “Buffered Voronoi Cell (BVC),” an algorithm originally proposed for multi-agent collision avoidance. After appropriate adaptation and new proposition in implementation of BVC, the experiments of folding and spreading a handkerchief are performed, and the results in simulation and robot experiments are presented and discussed for the validation and evaluation of entire system.

show abstract

Learning Visual Feedback Control for Dynamic Cloth Folding

Cited by 24 publications

References 19 publications

QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation

QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation

ShakingBot: dynamic manipulation for bagging

Development of the “Quad-SCARA” platform and its collision avoidance based on Buffered Voronoi Cell

Contact Info

Product

Resources

About