Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review

Arriola-Rios, Veronica; Güler, Püren; Ficuciello, Fanny; Kragić, Danica; Siciliano, Bruno; Wyatt, Jeremy L.

doi:10.3389/frobt.2020.00082

Cited by 82 publications

(47 citation statements)

References 131 publications

(183 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e factors k 3 and k 4 in the adaptive law are 5 and 1, respectively. In the controller, k 2 is 30 and k f is 0.4 * diag (3,4,4,4,4,3,2). e real-time ratio when debugging Gazebo ranges from 0.92 to 0.97, and the comparison effect with the PD control method of selecting appropriate PID parameters is shown in Figure 7.…”

Section: Simulation Of Coordinated Operationmentioning

confidence: 99%

“…Particularly, in the face of some complex operation tasks, the advantages of dual-arm robots are more obvious, such as carrying heavy objects and flexible assembly. us, it has attracted more attention of researchers [1][2][3]. e dual-arm robot is not just a simple superposition of two single-arm robots but cooperates with each other in the same system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization Control of Cooperative Trajectory towards Dual Arms Based on Time-Varying Constrained Output State

Zhang

Zha

et al. 2021

Complexity

View full text Add to dashboard Cite

Aiming at the impact and disturbance of dual-arm robots in the process of coordinated transportation, a dual-arm cooperative trajectory optimization control based on time-varying constrained output state is proposed. According to the constraint relationship of the end-effector trajectory of the dual-arm coordinated transportation, the joint space trajectory mathematical model of the dual-arm coordinated transportation was established by using the master-slave construction method. Based on the time impact optimization index of joint trajectory, a multiobjective nonlinear equation is established. Using random probability distribution to extract the interpolation features of nonuniform quintic B-spline trajectory, the feature optimization target is selected, and the Newton numerical algorithm is used for iterative optimization. At the same time, it is combined with an elite retention genetic algorithm to further optimize the target. Based on the disturbance and tracking problem, a PD control method based on time-varying constrained output state is proposed, and the control law is designed. Its convergence is verified by establishing the Lyapunov function equation and asymmetric term. The trajectory optimization results show that the proposed trajectory optimization method can increase the individual diversity and enhance the individual local optimization, thus avoiding the premature impact of the elite retention genetic algorithm. Finally, the proposed control method is simulated on the platform of Gazebo; compared with the traditional PD control method, the results show that the proposed control algorithm has high robustness, and the rationality of the coordinated trajectory control method is verified by the double-arm handling experiment.

show abstract

Section: Simulation Of Coordinated Operationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimization Control of Cooperative Trajectory towards Dual Arms Based on Time-Varying Constrained Output State

Zhang

Zha

et al. 2021

Complexity

View full text Add to dashboard Cite

show abstract

“…There has been a lot of work in the area of robotic manipulation of deformable objects [ 22 ]. The deformable object handling problem has been studied via classical methods such as motion planning and manipulation [ 23 ]. There has been recent interest in combining deep generative models with structured dynamical systems in the context of variational autoencoders, where the latent space is continuous [ 24 ].…”

Section: Related Workmentioning

confidence: 99%

Action Generative Networks Planning for Deformable Object with Raw Observations

Sheng

Jin

et al. 2021

Sensors

View full text Add to dashboard Cite

Synthesizing plans for a deformable object to transit from initial observations to goal observations, both of which are represented by high-dimensional data (namely “raw” data), is challenging due to the difficulty of learning abstract state representations of raw data and transition models of continuous states and continuous actions. Even though there have been some approaches making remarkable progress regarding the planning problem, they often neglect actions between observations and are unable to generate action sequences from initial observations to goal observations. In this paper, we propose a novel algorithm framework, namely AGN. We first learn a state-abstractor model to abstract states from raw observations, a state-generator model to generate raw observations from states, a heuristic model to predict actions to be executed in current states, and a transition model to transform current states to next states after executing specific actions. After that, we directly generate plans for a deformable object by performing the four models. We evaluate our approach in continuous domains and show that our approach is effective with comparison to state-of-the-art algorithms.

show abstract

“…Thereby, the grasp stability can be computed in real-time while the contact surfaces evolve during deformation. This evolution of the object surface is obtained by sampling mechanical deformation models [34], mainly mass-spring systems ( [35,36]), finite element methods (FEM) ( [37,38]), and impulse-based methods ( [39]). The mass-spring system is a fast and interactive physical model with a solid mathematical foundation and well-understood dynamics.…”

Section: Introductionmentioning

confidence: 99%

Grasp Planning Pipeline for Robust Manipulation of 3D Deformable Objects with Industrial Robotic Hand + Arm Systems

Zaidi¹,

Ramón

Sabourin

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In the grasping and manipulation of 3D deformable objects by robotic hands, the physical contact constraints between the fingers and the object have to be considered in order to validate the robustness of the task. Nevertheless, previous works rarely establish contact interaction models based on these constraints that enable the precise control of forces and deformations during the grasping process. This paper considers all steps of the grasping process of deformable objects in order to implement a complete grasp planning pipeline by computing the initial contact points (pregrasp strategy), and later, the contact forces and local deformations of the contact regions while the fingers close over the grasped object (grasp strategy). The deformable object behavior is modeled using a nonlinear isotropic mass-spring system, which is able to produce potential deformation. By combining both models (the contact interaction and the object deformation) in a simulation process, a new grasp planning method is proposed in order to guarantee the stability of the 3D grasped deformable object. Experimental grasping experiments of several 3D deformable objects with a Barrett hand (3-fingered) and a 6-DOF industrial robotic arm are executed. Not only will the final stable grasp configuration of the hand + object system be obtained, but an arm + hand approaching strategy (pregrasp) will also be computed.

show abstract

Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review

Cited by 82 publications

References 131 publications

Optimization Control of Cooperative Trajectory towards Dual Arms Based on Time-Varying Constrained Output State

Optimization Control of Cooperative Trajectory towards Dual Arms Based on Time-Varying Constrained Output State

Action Generative Networks Planning for Deformable Object with Raw Observations

Grasp Planning Pipeline for Robust Manipulation of 3D Deformable Objects with Industrial Robotic Hand + Arm Systems

Contact Info

Product

Resources

About