In order to solve the insufficient redundancy problem and slow convergence in multiple end-effector tasks, a piecewise varying-gain dual-criterion optimization (PVDO) method is proposed for motion planning of insufficient redundant manipulators. To achieve this, the convergence coefficients are designed to be piecewise varying, and the end-effector task is divided into two phases. In the initial phase, only the end-effector position task is considered and the fixed coefficient convergence method is adopted, which can take into consideration both end-effector task and secondary task optimization. In the second phase, the end-effector position and orientation are taken into account concurrently, and time-varying coefficients are used for end-effector task. The convergence coefficients are time varying to enhance the convergence speed, particularly when the errors are small in the later phase of task planning. This can ensure the optimization of secondary tasks when the manipulator is insufficient-redundant, and accomplish the end-effector task planning in a relatively fast speed. Finally, experiments are conducted to demonstrate the effectiveness of the proposed PVDO method in obstacle avoidance and joint limits avoidance.

To address the motion generation problem in distributed multimanipulator system operating in obstacles environment, a distributed slack barrier recurrent neural network (DSB-RNN) is proposed in this article. First, the communication topology among the multimanipulator system is summarized using an undirected graph representation. Then, the communication constraints and positions of the multimanipulators collaborative system are formulated as equality constraints with coupling variables. Additionally, nonstrict inequality constraints for obstacle avoidance and bilateral constraints for the manipulator joints are taken into account. Based on minimum velocity norm optimization criterion, the problem of motion generation for distributed multimanipulator system in obstacles environment is transformed into a time-varying quadratic programming problem. Next, a Lagrangian function is established and summarized as the original Karush–Kuhn–Tucker (KKT) conditions. To make this special time-varying problem solvable, barrier parameters and slack parameters are designed to improve the KKT conditions. Based on the improved KKT conditions and neurodynamics formula, a distributed recurrent neural network DSB-RNN is proposed. Experimental results demonstrate the effectiveness and accuracy of the proposed DSB-RNN method, and comparisons with other methods verify its advantages in terms of applicability and precision.

To enable distributed multiple mobile manipulator systems to complete collaborative tasks safely and stably, this article investigates and presents a motion generation scheme that considers both orientation and position coordination based on a distributed recurrent neural network. Moreover, physical limits are also considered. Specifically, the orientation and position coordination constraints and physical limits are modeled separately as equality and inequality constraints with coupled variables. Subsequently, a motion generation scheme for multiple mobile manipulators based on quadratic programming is established. Finally, a distributed linear variational inequality-based primal-dual neural network is constructed to solve the motion generation scheme and obtain the motion trajectories of all the mobile manipulators. The simulation results demonstrate that the hybrid orientation and position collaboration motion generation scheme effectively addresses the position and orientation coordination problem for multiple mobile manipulator systems. Compared to other schemes, the proposed scheme based on a distributed computing structure greatly enhances the stability of the system. Additionally, the proposed approach introduces orientation coordination and physical limits, which increases the practicality of the system.

To address the real-time motion generation problem of a multimanipulator collaborative system, a novel distributed varying-parameter recurrent neural network (DVP-RNN) is proposed in this article. First, an undirected graph is used to simplify the communication topology of the multimanipulator collaborative system. Then, the communication and coupled constraints of the multimanipulator collaborative system are expressed as equality constraints with coupled variables. The physical limits (i.e., angular limits and angular velocity limits) of the multimanipulator collaborative system are expressed as inequality constraints. Based on the minimum velocity norm optimization criterion, a quadratic programming problem with coupled variables and constraints is employed to formulate the motion generation problem of a multimanipulator collaborative system. Finally, a DVP-RNN is designed to solve the quadratic programming problem with coupled variables and constraints to obtain the joint trajectory of the multimanipulator collaborative system. Simulations show that the proposed DVP-RNN can effectively solve the motion generation problem of a multimanipulator collaborative system. Comparisons confirm the superiority of the DVP-RNN in terms of applicability and precision.

Soft wires of robot operating tools often interfere with end-effector tasks in practical automated production scenarios. In order to avoid soft wires of industrial robot manipulators executing end-effector tasks, a real-time 3-D visual detection-based soft wire avoidance (3D-VDWA) scheme is proposed, which considers the soft wire detection and location, the soft wire avoidance, and the motion planning at the same time. The proposed 3D-VDWA includes three modules: 1) perception module; 2) motion planning module; and 3) soft wire avoidance module. The perception module is based on hue–saturation–value (HSV) range and depth information to detect and locate soft wires. The motion planning module is based on the method of the pseudo-inverse matrix to plan the path of the manipulator to the target position and orientation. The soft wire avoidance module is based on the Jacobian transpose method to dynamically avoid soft wire obstacles in the process of movement. Experiments demonstrate the effectiveness and the feasibility of the proposed scheme to solve the motion planning problem with soft wire avoidance of industrial manipulators for end-effector tasks.

As an effective measure to capture the object of interest in video sequence, video salient object detection (VSOD) requires the processing of information from spatial-motion modalities, although plenty of traditional VSOD models were dedicated to developing efficient spatial and motion features to obtain salient objects of global consistency, the highly redundant spatial information brought by consecutive identical objects will inevitably reduce the generalization ability of these VSOD model. Although exploring the integration of spatial and motion information can improve the inter-frame correlation of salient objects to some extent, previous models tend to focus only on simple spatio-temporal fusion, which can also lead to the generation of redundant information, resulting in poor detection performance. Therefore, it is necessary to focus on effectively fusing the feature information of different modalities to eliminate the effect of redundant information. In this research, we proposed a self-attentive multilayer cross-stacking fusion based VSOD model, which productively extracts the multimodal features for two-way information transfer, fully utilizes the spatial and temporal knowledge to complement each other, and refines the cross-stacking of the interacted information and spatial features for local and global saliency optimization. As a result, the redundant spatial information can be largely eliminated, reducing the misidentification of salient objects due to blurred backgrounds or moving objects, and adaptively activating more weights of the salient object to achieve globally consistent saliency. Comprehensive experiments on four publicly available VSOD datasets demonstrated that the model had superior performance compared to the latest multiple VSOD models.

Most colorectal cancers originate from adenomatous polyps, which start as single asymptomatic polyps and develop into malignant tumors. In clinical practice, colonoscopy is an extremely effective method for detecting polyps, and it provides important visual information for the accurate identification and removal of polyps. However, it is highly challenging to achieve accurate segmentation of various polyps due to the complex and variable size, shape, color, number, and growth background of polyps at different periods. To address these dilemmas, we propose a multi-distance feature dissimilarity-guided encoder-decoder network for automatic polyp segmentation, mainly consisting of the Multi-Distance Differential Module (MDDM) and the Hybrid Loss Module (HLM). The former mainly utilizes the multilayer feature subtraction (MLFS) operations to extract the difference information between short-distance adjacent layer features and short-distance and long-distance cross-layer features. Given this, the pyramid-inspired MDDM obtains discriminative features continuously between adjacent/cross layers, enhancing complementary features between different layers. The latter supervises the feature maps extracted at each network level to achieve finer predictions. Experiments on four challenge datasets confirm that the proposed model outperforms most state-of-the-art methods in six evaluation metrics while yielding reasonably accurate segmentation results.