Grasp evaluation and planning are two fundamental issues in robotic grasping and dexterous manipulation. Most traditional methods for grasp quality evaluation suffer from non-uniformity of the wrench space and a depen...Grasp evaluation and planning are two fundamental issues in robotic grasping and dexterous manipulation. Most traditional methods for grasp quality evaluation suffer from non-uniformity of the wrench space and a dependence on the scale and choice of the reference frame. To overcome these weaknesses, we present a grasp evaluation method based on disturbance force rejection under the assumption that the normal component of each individual contact force is less than one. The evaluation criterion is solved using an enhanced ray-shooting algorithm in which the geometry of the grasp wrench space is read by the support mapping. This evaluation procedure is very fast due to the efficiency of the ray-shooting algorithm without linearization of the friction cones. Based on a necessary condition for grasp quality improvement, a heuristic searching algorithm for polyhedral object regrasp is also proposed. It starts from an initial force-closure unit grasp configuration and iteratively improves the grasp quality to find the locally optimum contact points. The efficiency and effectiveness of the proposed algorithms are illustrated by a number of numerical examples.展开更多
Humans can quickly perform adaptive grasping of soft objects by using visual perception and judgment of the grasping angle,which helps prevent the objects from sliding or deforming excessively.However,this easy task r...Humans can quickly perform adaptive grasping of soft objects by using visual perception and judgment of the grasping angle,which helps prevent the objects from sliding or deforming excessively.However,this easy task remains a challenge for robots.The grasping states of soft objects can be categorized into four types:sliding,appropriate,excessive and extreme.Effective recognition of different states is crucial for achieving adaptive grasping of soft objects.To address this problem,a novel visual-curvature fusion network based on YOLOv8(VCFN-YOLOv8)is proposed to evaluate the grasping state of various soft objects.In this framework,the robotic arm equipped with the wrist camera and the curvature sensor is established to perform generalization grasping and lifting experiments on 11 different objects.Meanwhile,the dataset is built for training and testing the proposed method.The results show a classification accuracy of 99.51% on four different grasping states.A series of grasping evaluation experiments is conducted based on the proposed framework,along with tests for the model's generality.The experiment results demonstrate that VCFN-YOLOv8 is accurate and efficient in evaluating the grasping state of soft objects and shows a certain degree of generalization for non-soft objects.It can be widely applied in fields such as automatic control,adaptive grasping and surgical robot.展开更多
文摘Grasp evaluation and planning are two fundamental issues in robotic grasping and dexterous manipulation. Most traditional methods for grasp quality evaluation suffer from non-uniformity of the wrench space and a dependence on the scale and choice of the reference frame. To overcome these weaknesses, we present a grasp evaluation method based on disturbance force rejection under the assumption that the normal component of each individual contact force is less than one. The evaluation criterion is solved using an enhanced ray-shooting algorithm in which the geometry of the grasp wrench space is read by the support mapping. This evaluation procedure is very fast due to the efficiency of the ray-shooting algorithm without linearization of the friction cones. Based on a necessary condition for grasp quality improvement, a heuristic searching algorithm for polyhedral object regrasp is also proposed. It starts from an initial force-closure unit grasp configuration and iteratively improves the grasp quality to find the locally optimum contact points. The efficiency and effectiveness of the proposed algorithms are illustrated by a number of numerical examples.
基金supported by the Fundamental Research Project of Shanxi Province(202403021211229).
文摘Humans can quickly perform adaptive grasping of soft objects by using visual perception and judgment of the grasping angle,which helps prevent the objects from sliding or deforming excessively.However,this easy task remains a challenge for robots.The grasping states of soft objects can be categorized into four types:sliding,appropriate,excessive and extreme.Effective recognition of different states is crucial for achieving adaptive grasping of soft objects.To address this problem,a novel visual-curvature fusion network based on YOLOv8(VCFN-YOLOv8)is proposed to evaluate the grasping state of various soft objects.In this framework,the robotic arm equipped with the wrist camera and the curvature sensor is established to perform generalization grasping and lifting experiments on 11 different objects.Meanwhile,the dataset is built for training and testing the proposed method.The results show a classification accuracy of 99.51% on four different grasping states.A series of grasping evaluation experiments is conducted based on the proposed framework,along with tests for the model's generality.The experiment results demonstrate that VCFN-YOLOv8 is accurate and efficient in evaluating the grasping state of soft objects and shows a certain degree of generalization for non-soft objects.It can be widely applied in fields such as automatic control,adaptive grasping and surgical robot.
