1,721,086 research outputs found
Model-based Manipulation of Deformable Linear Objects by Multivariate Dynamic Splines
Full text linkIn this paper, the modelling and the simulation of a Deformable Linear Object (DLO) manipulation are reported. The main motivation of this study is to define a strategy to enable a robotic manipulator to predict in real time the shape a DLO will achieve during the execution of a manipulation action. To accomplish this target in a reasonable time, according to the possibility of adopting this solution in an industrial manufacturing system, an approximate but physically consistent model of the DLO is adopted considering the predominant plasticity of the object to be manipulated, as in the case of electric cable manipulation. The DLO manipulation model is based on multivariate dynamic splines solved iteratively in real-time to interpolate the DLO shape during the manipulation sequence. The systems assumes to be able to detect the initial configuration of the DLO at each iteration of the algorithm by means of a proper vision system. Preliminary simulation results are presented to show the effectiveness of the method
New model-based manipulation technique for reshaping deformable linear objects
Full text linkIn this article, we consider the problem of reshaping a deformable linear object (DLO) like wires, cables, ropes, and surgical sutures. The solution to this problem would be useful for many fields, especially industrial manufacturing, where the DLO manipulation is still frequently carried out by human workers. In this work, a new model-based manipulation technique for reshaping a DLO is addressed employing a sequence of grasping and releasing primitives performed by a single-armed robot equipped with a gripper. A decision process selects the optimal grasping point exploiting an error minimization approach and chooses the related releasing point. This decision process performs a spline interpolation between the error values obtained from candidate grasping points and chooses the optimal point that owns a minimum error. The multivariate dynamic spline model of the DLO is exploited for selecting the optimal grasping point and predicting the DLO behavior during the manipulation process. Because of its advantages over other integration methods, the symplectic integrator is utilized for iteratively solving the DLO dynamic model. Simulation results of reshaping a DLO lying on a table are presented to evaluate the proposed technique. These results illustrate the intermediate deformation steps which lead the DLO from its starting state to the desired one. They demonstrate that our proposed technique can efficiently manipulate the DLO into various shapes in few steps
Pointcloud-based Identification of Optimal Grasping Poses for Cloth-like Deformable Objects
Full text linkIn this paper, the problem of identifying optimal grasping poses for cloth-like deformable objects is addressed by means of a four-steps algorithm performing the processing of the data coming from a 3D camera. The first step segments the source pointcloud, while the second step implements a wrinkledness measure able to robustly detect graspable regions of a cloth. In the third step the identification of each individual wrinkle is accomplished by fitting a piecewise curve. Finally, in the fourth step, a target grasping pose for each detected wrinkle is estimated. Compared to deep learning approaches where the availability of a good quality dataset or trained model is necessary, our general algorithm can find employment in very different scenarios with minor parameters tweaking. Results showing the application of our method to the clothes bin picking task are presented
Symplectic Integration for Multivariate Dynamic Spline-Based Model of Deformable Linear Objects
Full text linkDeformable linear objects (DLOs) such as ropes, cables, and surgical sutures have a wide variety of uses in automotive engineering, surgery, and electromechanical industries. Therefore, modeling of DLOs as well as a computationally efficient way to predict the DLO behavior is of great importance, in particular to enable robotic manipulation of DLOs. The main motivation of this work is to enable efficient prediction of the DLO behavior during robotic manipulation. In this paper, the DLO is modeled by a multivariate dynamic spline, while a symplectic integration method is used to solve the model iteratively by interpolating the DLO shape during the manipulation process. Comparisons between the symplectic, Runge-Kutta, and Zhai integrators are reported. The presented results show the capabilities of the symplectic integrator to overcome other integration methods in predicting the DLO behavior. Moreover, the results obtained with different sets of model parameters integrated by means of the symplectic method are reported to show how they influence the DLO behavior estimation
Design of a beam-based variable stiffness actuator via shape optimization in a CAD/CAE environment
No full textIndustrial robots are commonly designed to be very fast and stiff in order to achieve extremely precise position control capabilities. Nonetheless, high speeds and power do not allow for a safe physical interaction between robots and humans. With the exception of the latest generation lightweight arms, purposely design for human-robot collaborative tasks, safety devices shall be employed when workers enter the robots workspace, in order to reduce the chances of injuries. In this context, Variable Stiffness Actuators (VSA) potentially represent an effective solution for increasing robot safety. In light of this consideration, the present paper describes the design optimization of a VSA architecture previously proposed by the authors. In this novel embodiment, the VSA can achieve stiffness modulation via the use of a pair of compliant mechanisms with distributed compliance, which act as nonlinear springs with proper torque-deflection characteristic. Such elastic elements are composed of slender beams whose neutral axis is described by a spline curve with non-trivial shape. The beam geometry is determined by leveraging on a CAD/CAE framework allowing for the shape optimization of complex flexures. The design method makes use of the modeling and simulation capabilities of a parametric CAD software seamlessly connected to a FEM tool (i.e. Ansys Workbench). For validation purposes, proof-concept 3D printed prototypes of both non-linear elastic element and overall VSA are finally produced and tested. Experimental results fully confirm that the compliant mechanism behaves as expected
Validating DLO models from shape observation
Full text linkIn this paper, the problem of fitting the model of deformable linear objects from the observation of the shape under the effect of known external forces like gravity is taken into account. The model of the deformable linear object is based on dynamic splines, allowing to obtain a reliable prediction of the object behavior while preserving a suitable efficiency and simplicity of the model. The object shape is measured by means of a calibrated vision system, and a fitting between the observed shape and the theoretical model is defined for validation. Experiments are executed in different conditions, showing the reliability of the proposed spline-based model
Robotized Laundry Manipulation With Appliance User Interface Interpretation
No full textIn this paper, a robotized laundry picking and insertion in to washing machine followed by display interpretation and adjustment of the washing cycle for a complete robotic laundry operation is described. To ensure the successful insertion of a laundry, recovery picking from the drum door region in case large clothes remain partially out from the washing machine is also evaluated. A pointcloud-based perception algorithm is proposed to detect wrinkles on the cloth surface to compute spline curves along the wrinkle-like structure and estimate grasping frames. Even more, to insure graspability in the absence of wrinkles, a blob detection approach is evaluated together with grasp pose quality ranking to aim for the optimal pose. A deep learning based washing machine user-interface detection and interpretation algorithm is also developed, to fully Automate the robotic laundry operation. A fully autonomous laundry handling and washing cycle setting on the appliance display is tested and validated extensively by performing multiple tasks using our robotic platforms (Tiago and Baxter) and AEG washing machine
A cyber-physical system for clothes detection, manipulation and washing machine loading
Full text linkIn this paper, a cyber-physical system for the detection and manipulation of clothes and its application to the problem of their robotized insertion in a washing machine drum is presented. Starting with the clothes randomly placed inside a bin next to the appliance, the method describes the approach used for the laundry bin picking together with a recovery picking from the drum door region in case some large cloth remains partially out from the washing machine. The same pointcloud-based perception algorithm is utilized for both tasks: the approaches are different only for what concerns the segmentation of the pointcloud for the extraction of the cloth-related points. The main algorithm exploits a wrinkledness measure to identify wrinkles in the cloth surface, to robustly assign spline curves to the detected wrinkle-like structure and to estimate grasping frames. In addition, a pointcloud registration technique is applied in the washing machine recovery task for the segmentation stage. The planning of the robot operations to execute the cloth grasping is also presented. The approach has been validated extensively by performing 100 trials grasps for both tasks
Combining Hybrid Genetic Algorithms and Feedforward Neural Networks for Pallet Loading in Real-World Applications
No full textThe “Distributor’s Pallet Packing Problem” in a real industrial scenario is addressed in this paper. The main goal is to develop a two-stage algorithm capable to provide the spatial coordinates of the placed boxes vertices and also the optimal boxes input sequence, while guaranteeing geometric, stability, fragility constraints and a reduced computational time. Due to NP-hard complexity of the problem, a hybrid genetic algorithm coupled with a feedforward neural network is used. In the first stage, the hybrid genetic algorithm is run several times on each order within a large set of packing instances, using a different fitness weight vector at each iteration, and storing the best chromosomes to form a rich solution set. After its generation, the best solution is chosen for each order, optimizing a new global weighted function. The global optimal weight vector is tuned by hand, relying on a graphical user interface that allows to show, in real-time, the best solution as a function of the global weights. The dataset is then created, keeping track of both local and global weight vectors related to the optimal solution. Hence, the dataset is used to train, validate and test the neural network. In the second stage, the trained neural network is used to provide the optimal pair of fitness weight vectors, allowing to run the hybrid genetic algorithm only one time and to select directly the optimal solution in the set. The proposed algorithm has been tested and validated on several packing instances provided by an industrial company
Disturbance observer-based nonlinear feedback control for position tracking of electro-hydraulic systems in a finite time
Full text linkIn this paper, a disturbance observer-based backstepping tracking control is designed for an electro-hydraulic actuator (EHA) system to estimate and track reference signals in a finite time. It is assumed that the system is uncertain with unknown upper bounds. Different from the existing ones, the proposed observer can deal with strong uncertainties in which the estimation error converges to an arbitrarily small neighborhood of zero in a finite time. Then, the disturbance observer-based backstepping tracking control is provided to compensate the uncertainties and estimation errors and to guarantee the finite-time tracking of the piston position toward the desired time-varying reference signal. The key idea is to employ a monotonically increasing function associated with the control objective to improve the control performance, where the finite-time boundedness criterion is guaranteed using Lyapunov stability analysis. Finally, the efficacy of the proposed robust scheme for the EHA system with unknown measurement noise is illustrated in numerical simulations as compared to a leading observer-based control strategy in the literature. It is shown that the proposed approach results in more accuracy and faster convergence than that in the literature, making it a qualified alternative approach with noteworthy potential
- …
