In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated dat...
详细信息
Fragile fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry. With the aging of the global population, it is supposed to develop robotic grasping systems to replace manual...
详细信息
Fragile fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry. With the aging of the global population, it is supposed to develop robotic grasping systems to replace manual labor. However, damage-less grasping of fragile fruit is the key problem in robotization. Inappropriate grasping force will result in damage, early-stage bruise, or slip. Benefits from the advantages of softness and compliance of a pneumatic-driven soft gripper have been widely adopted for agricultural product and food manipulation. Nevertheless, pneumatic gripper is a complex, multivariable, nonlinear, and long time-delay control system, which is difficult to achieve robust closed-loop grasping force control. In this study, we aim to solve this problem and developed a robotic grasping force control system with pneumatic gripper and matrix force sensor. The force distribution condition was explored to tackle the problem in changing of the main contact point. A double closed-loop control method was proposed based on Kalman filter (KF) and proportion integration differentiation controller with dead band. The external and internal control loops were force controller and air pressure of the pump controller, respectively. The double closed-loop controller with dead band achieved robust grasping force control through air pressure. The experimental results validated the effectiveness of the KF method for denoising and the matrix force visualization method for exploring grasping mechanism. Ablation studies were carried out to demonstrate the effectiveness of the multiple grasping force sensing units in matrix form and the dead band in the controller. The maximum steady-state error was 0.07 N. In addition, the generalization performance and the antidisturbance ability of the grasping force control system was also validated. In summary, the problem in closed-loop control of the grasping force for pneumatic gripper has been solved in our study, and the method in
In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated dat...
详细信息
Fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry, which involve continuous pick-and-place manipulation. In this case, we aim to replace manual working with robotic gra...
详细信息
Fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry, which involve continuous pick-and-place manipulation. In this case, we aim to replace manual working with robotic grasping. However, for robotic fragile fruit grasping, the main difficulty is to reduce early stage bruise while maintaining the grasping reliability. In this study, we aim to solve this problem and achieve reliable and damageless robotic fragile fruit grasping. Inspired by the structure of the Asian elephant trunk with its feeding behavior, a bionic and pneumatic soft gripper was designed, and a multimodal grasping strategy was proposed. Similar with Asian elephant trunk, the gripper has two designed trapezoid air chambers to control the two individual parts, including fingertip-like process and enveloping structure. Enveloping grasping behavior was imitated with larger area of contact, less contact force, and larger pull off force. A visuo-tactile multimodal grasping strategy was integrated into the robotic grasping system. The visual modality was developed for positioning and grasp pose estimation. The tactile modality was employed for grasping pose confirmation and closed-loop grasping force control. In the experiment on the enveloping gripper, the maximum contact force and the pull off force reached a good balance and were 0.7083 N and 7.959 N, respectively. With the proposed multimodal grasping strategy, the grasping success rate increased 4.23 % to 96.70 %. As for closed-loop control of the grasping force, the average value for steady-state error and maximum overshoot were 0.0856 N and 26.43 %, respectively. The experiment on Spatial Frequency Domain Imaging (SFDI) demonstrated the effectiveness of our enveloping gripper in reducing the early stage bruise. To some extent, the designed enveloping gripper with the proposed multimodal strategy could achieve reliable and damage-less fragile fruit grasping, which is promising in fruit postharvest industr
This article studies input design of kernel-based regularization methods for linear dynamical systems, which has been formulated as a nonconvex optimization problem with the criterion being a scalar measure of the pos...
详细信息
This article studies input design of kernel-based regularization methods for linear dynamical systems, which has been formulated as a nonconvex optimization problem with the criterion being a scalar measure of the posterior covariance of the Bayesian estimate, subject to a spherical constraint on the input. The nonconvex nature of such input design problems poses significant challenges in deriving optimality conditions and efficient numerical algorithms. In this work, we first derive a sufficient condition for guaranteeing that a stationary point of the regularized input design problem is a global minimum. Next, we propose a spherical constraint preserving (SCP) algorithm to efficiently reach a stationary point of the design problem. Numerical simulation results show that the SCP algorithm finds the global minimum of the original design problem for all simulated cases and its average computational time is only approximately one tenth of that of the algorithms for previous methods.
Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the fe...
详细信息
暂无评论