“…A preset desired grasping force is further achieved and the relative finger orientation is adjusted with the use of a tunable control parameter. Preliminary results of this work are reported in Grammatikopoulou et al [41] for fingers with rigid tips. In this work, the proposed controller and its stability are analyzed for the more realistic soft fingertip case and is extensively validated by both simulations and experiments conducted on a prototype robotic hand setup with various object shapes.…”
Section: Introductionmentioning
confidence: 55%
“…This controller was proved to achieve the control objective in the case of fingers with rigid tips. 41 In this work, we prove (Section 5) that the proposed controller (11), (12) achieves the control objectives in the case of soft fingertips and hence it can be successfully utilized in either case. Remark 1.…”
Section: Grasp and Finger Relative Orientation Controlmentioning
confidence: 78%
“…[32][33][34] This class of controllers achieves stable grasping and fine manipulation without any force and contact sensing requirements for objects with flat surfaces and arbitrary shape for both the 2D and 3D cases. 7,[35][36][37][38][39][40][41] As the initial finger-object pose and contact positions must not necessarily correspond to an equilibrium state, perception and execution errors can be accommodated.…”
SUMMARYThere is a large gap between reality and grasp models that are currently available because of the static analysis that characterizes these approaches. This work attempts to fill this need by proposing a control law that, starting from an initial contact state which does not necessarily correspond to an equilibrium, achieves dynamically a stable grasp and a relative finger orientation in the case of pinching an object with arbitrary shape via rolling soft fingertips. Controlling relative finger orientation may improve grasping force manipulability and allow the appropriate shaping of the composite object consisted of the distal links and the object, for facilitating subsequent tasks. The proposed controller utilizes only finger proprioceptive measurements and is not based on the system model. Simulation and experimental results demonstrate the performance of the proposed controller with objects of different shapes.
“…A preset desired grasping force is further achieved and the relative finger orientation is adjusted with the use of a tunable control parameter. Preliminary results of this work are reported in Grammatikopoulou et al [41] for fingers with rigid tips. In this work, the proposed controller and its stability are analyzed for the more realistic soft fingertip case and is extensively validated by both simulations and experiments conducted on a prototype robotic hand setup with various object shapes.…”
Section: Introductionmentioning
confidence: 55%
“…This controller was proved to achieve the control objective in the case of fingers with rigid tips. 41 In this work, we prove (Section 5) that the proposed controller (11), (12) achieves the control objectives in the case of soft fingertips and hence it can be successfully utilized in either case. Remark 1.…”
Section: Grasp and Finger Relative Orientation Controlmentioning
confidence: 78%
“…[32][33][34] This class of controllers achieves stable grasping and fine manipulation without any force and contact sensing requirements for objects with flat surfaces and arbitrary shape for both the 2D and 3D cases. 7,[35][36][37][38][39][40][41] As the initial finger-object pose and contact positions must not necessarily correspond to an equilibrium state, perception and execution errors can be accommodated.…”
SUMMARYThere is a large gap between reality and grasp models that are currently available because of the static analysis that characterizes these approaches. This work attempts to fill this need by proposing a control law that, starting from an initial contact state which does not necessarily correspond to an equilibrium, achieves dynamically a stable grasp and a relative finger orientation in the case of pinching an object with arbitrary shape via rolling soft fingertips. Controlling relative finger orientation may improve grasping force manipulability and allow the appropriate shaping of the composite object consisted of the distal links and the object, for facilitating subsequent tasks. The proposed controller utilizes only finger proprioceptive measurements and is not based on the system model. Simulation and experimental results demonstrate the performance of the proposed controller with objects of different shapes.
“…However in related work, the control solution causes an induced rolling disturbance, which requires additional control terms for compensation [36]. In the proposed formulation presented here, the effect of no external information manifests as a disturbance which is similarly a function of the proposed manipulation and internal force control terms as seen in (30). However the proposed control neatly compensates for these disturbances without requiring any additional control terms, and furthermore rejects unknown external disturbances which are not accounted for in the related blind grasping work [36,35].…”
Tactile-based blind grasping addresses realistic robotic grasping in which the hand only has access to proprioceptive and tactile sensors. The robotic hand has no prior knowledge of the object/grasp properties, such as object weight, inertia, and shape. There exists no manipulation controller that rigorously guarantees object manipulation in such a setting. Here, a robust control law is proposed for object manipulation in tactile-based blind grasping. The analysis ensures semi-global asymptotic and exponential stability in the presence of model uncertainties and external disturbances that are neglected in related work. Simulation and hardware results validate the effectiveness of the proposed approach.
“…There have also been approaches proposed in which arbitrary object shapes were grasped with an optimal force and angle without requiring contact information; however, while success was achieved in simulations, experimental success is yet to be reported. 11,12 Recently, several studies have looked into using training from visual data to achieve object classification by convolutional neural networks (CNNs), and thereby obtain the grasping points for the given object. 15,16 There has been particular emphasis on grasping various objects using a given gripper by using a Kinect sensor or RGB camera, without changing hardware specifications.…”
SUMMARY
Optimal grasping points for a robotic gripper were derived, based on object and hand geometry, using deep neural networks (DNNs). The optimal grasping cost functions were derived using probability density functions for each local cost function of the normal distribution. Using the DNN, the optimum height and width were set for the robot hand to grasp objects, whose geometric and mass centre points were also considered in obtaining the optimum grasping positions for the robot fingers and the object. The proposed algorithm was tested on 10 differently shaped objects and showed improved grip performance compared to conventional methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.